RESEARCH METHODOLOGY
(BUMA-331)
Rift Valley University College
Center for Distance Education
Adama 2010
CHAPTER ONE
CONCEPTS AND ELEMENTS OF RESEARCH
1.1 The Nature of Research: Introductions to Research
Some of definitions of Research are quoted here

Research is sufficiently objective and systematic to make possible classification,
generalization and reification of the date observed. ( Lund berg)

It is essentially a systematic inquiry seeking facts through objectively verifiable methods
in order to discover the relation ship among them and to deduce from them broad
principles or laws. (M.H.Gopal)

It is the Manipulation of things, concepts or symbols for the purpose of generalizing and
to extent, correct or verify knowledge, whether that knowledge aids in construction of a
theory or in practice of an art. (D. Slesinger and M.Stepheson Encyclopedia of Social
Sciences)

Research refers to a critical and exhaustive investigation of experimentation having as its
aim the revision of accepted conclusions in the light of new discovered facts.
(The Encyclopaedia of social Science, Mac – millan)

Research is a careful inquiry or examination in seeking facts or principles, a diligent
investigation to ascertain something (- Clifford Woody)
Research is a means by which you will be able to acquire knowledge. For your understanding
of how it is help full to acquire knowledge you need to know about its meaning and
characteristics.
Further Emory and cooper defined Research as, “It is any organized inquiry carried out to
provide information for the solution of a problem”. Research is an investigation undertaken
in order to discover new facts, get additional information, etc. In general research can be
defined as an inquiry in to the nature of, the reasons for, and the consequences of any
particular set of circumstances, either these circumstances are experimentally controlled or
recorded just as they occur. Research can be a means to an end or an end in it self.
1
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
Both are perfectly valid uses, but each entails a rather different approach to the definition of
the problem at hand and formulation of objectives.
In simple words research can be defined as any scholarly investigation in search for truths,
for facts, for certainties. (Gupta,S. ----) human being do not
operate under controlled
conditions, on the contrary, they are always under the diverse influences such as
environmental, psychological and Social and these influences freely interaction with each
other and seldom operate in isolation. The complexity is further in testified by the uniqueness
of each individual’s behavior. Trial and error method can no longer be appreciated and
decision is to be accurate and timely and should be based on facts and realities. It is in this
context that business decisions are now tremendously influenced by research and research
findings.
While searching for a definition of research the novice research is Likely to get various
definitions. This is because the term is used in different ways by different authorities Let us
see how some leaders in the area have defined it.
Research is the manner in which we solve knotty problems in our attempt to push back
the frontiers of human ignorance. Research is ultimately a way of thinking. It is a way of
looking at accumulated fact so that a collection of data speaks to the mind of the
researcher.
Research can be defined as any scholarly investigation in search for truths, or for
certainties.
Research is essentially a systematic inquiry seeking facts through objectively verifiable
methods in order to discover the relation ship among them and to deduce from it the
broad principles /Laws.
Research refers to a critical and exhaustive examination / investigation of
experimentation having as its aim the revision of accepted conclusion in the light of new
discovered facts.
Research is the process of arriving at dependable solutions to problems through the
planned and systematic collection, analysis and interpretation of data
2
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
Research is the activity of solving problems which leads to new knowledge using
methods of inquiry which are currently accepted as adequate by scholars in the field.
Research is a systematic, controlled empirical and critical investigation of hypothetical
propositions about the presumed relations among natural phenomena. The terms
systematic and controlled in this definition refer to the degree to which the observations
are controlled and alternative explanations of the outcome are ruled out. On the other
hand the terms empirical and critical point to the requirements for the researcher to test
subjective beliefs against objective reality and have the findings open to further scrutiny
(detailed examination) and testing.
Therefore, the best research should be reliable, variable and exhaustive.
Research starts with a problem, collection of data or facts, analyzing them critically, and
reaching to decisions based on the actual evidence.
In general, a synthesis of the above definitions indicates that research is structured inquiry
that utilizes acceptable scientific methodology to solve problems and creates newly
applicable knowledge.
1.1.1 Some Characteristics of Research
According to John Best, a summary of some of the characteristics of Research had made to
clarify its methodology.
 Research is directed towards the solution of a problem. It may attempt to answer a
question or to determine the relation between two or more variables ;
 Research emphasizes the development of generalization, principles of theories that will
be helpful in predicting future occurrence ;
 Research is based up on observable experience or empirical evidence ;
 Research demands accurate observations and descriptions ;
 Research involves gathering new data from primary or first hand sources or using
existing data for a new purpose ;
 Research requires expertise. The researcher knows what is already known about the
problem and how others have investigated it ;
 Research Strives to be objective and logical, applying every possible test to validate the
procedure employed, the data collected, and the conclusions reached ;
3
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)

Research is characterized by patient and un unhurried activity ;

Research is carefully recorded and reported, and

Research sometimes requires courage.
1.1.2 Classification of Research
There are two broad classification of research
A.
Research in physical or natural sciences.
B.
Research in Social or human sciences.
Physical Science deal with things, which can be put to laboratory tests under guided
conditions.
These researches deal with physical phenomena upon which man has complete control.
Researches in social sciences are based on human behavior, which is influenced by so many
factors such as physical, social, temperamental, psychological, and economic. We can never
hope to put such human beings to laboratory testes. Even, if it is done, their responses would
not be natural but subject to the awareness of the artificial conditions.
1.1.3 Social Research
Social research is that part of research, which studies human behavior on a part of sociality.
Social research is to find explanation to unexplained social phenomena, to clarify doubts and
correct the misconceived facts of social Life. The complexity of human or social data can
largely be attributed to this.
To have knowledge for the sake of knowledge is termed as pure research, but gathering
knowledge that could aid in the better meat of human destiny is known as applied research. It
is very difficult to draw demarcation between these two types of research, as each is
dependent on the other for development and verification.
Social research can be defined as; the part of research which studies human behavior as a part
of society.
1.1.4 Characteristics of Social Research
Social Research is devoted to a study of mankind in his social environment and is concerned
with improving his understanding of social orders, groups, institutions and ethics. (Rummel).
Systematized investigation to gain new knowledge about social phenomena and surveys, we
call social research. (prof. C. A. Moser).
4
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
From the above few, but more, accepted definitions the following characteristics of social
research may be drawn
A. Social Research Deals with Social Phenomena
It studies the behavior of human being as members of a social and their feelings, responses
and attitudes under different circumstances. It encompasses the study of social phenomena
covering economic, political, Social, educational, administrative and related aspects of social.
Life also the Social groups and institutions. Thus, the social research was born out to solve
man’s problem.
B. Social Research Aims at Discovering of New Facts
The scientific research techniques are applied to find out truth reasoning or relationship of
various kinds of human behavior.
C. Social Research is a Scientific Undertaking
Social research is a scientific undertaking in which logical and systematized techniques are
used. Social research also develops new scientific tools and concepts which facilitate reliable
and valid study of human behavior.
D. Social Research Assists in the Understanding of Evolution of New Theories
Every research highlights some broad principles, establishes some scientific truth and
analyses their sequences, inter-relationships and casual explanations. This results in
expansion of knowledge, improvement in the understanding of the social phenomena and in
the evolution of new theories.
E. Social research requires deep knowledge and minute investigation of the topic
concerned.
F.
Social Research must be objective
Researcher should not take his own interest because any personal bias vitiates (lowers the
quality of) the universality criterion of a scientific preposition.
G. In Social Research, We Study Social Phenomena or Human Behavior
Since in social research, we study social phenomena or human behavior, therefore,
experimentation is not possible in social sciences. However, in some cases social sciences
take shelter of controlled experimentation.
5
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
H. In Social Research Inter – relationship between Variables Understudy is Must
Besides it, the variables of social research study can not be measured correctly; only rough
estimation of variables is possible.
I.
Social Research is of Dynamic Nature
Social research is of dynamic nature; therefore, what was true of past might not be true of
present.
J.
Social Research in Any Field is Inter-related
Therefore, we can not draw water – tight compartments for each sector or we can not say
whether it is purely political, economical or sociological research.
K. Social research fells that the social events are also governed by the rules and regulations
as Physical events.
L. Research is Social Science is Complimentary to Research in Physical Science
Research is social science is complimentary to research in physical science and actually both
branches of knowledge help each other and the way to progress. In this context Good and
Scats states. “ The good life makes demand on all fields of science. The problems of
producing a good life are in part Physiological in part biological and in part physiological or
sociological. Man finds his need distribution through all areas of knowledge and he like wish
finds his satisfaction arising from the meeting of his need in all areas. Continued study and
research programs must, therefore, be maintained over a broad range of interest.”
1.1.5 Motivating Factors of Social Research
P.V Young has mentioned four motivating factors of social research.
A. Curiosity about Unknown
In his own words “Curiosity is an intrinsic trait of human mind and a compelling drive in the
exploration of man’s surroundings”. It is natural instinct in the making. A man is always
curious about the unknown and mysterious objects that he notices around him and tries to
understand them in his own.
B. Desire to Understand the Cause and Effect Relationship of Social Problems
According to P.V. Yong “the research of cause and effect relationship has been more
relentless than almost any other scientist effort up on which human energies have been spent.
People want not only the results of the events but also want to know how they have
6
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
happened. What was their cause and what was their effect? The research is undertaken to
remove doubts and uncertainties which result from misconceptions about social phenomena
C. Appearance of New and Unexpected Situations
In a modern complex and dynamic world a man is often faced with many acute and difficult
problems. It is the duty of the social scientist to find out their real cause and suggests
solutions to such problems.
D. Desire to Discover New and Test Old Scientific Procedures
It concerns with the technique or methods used in social research. Social scientists have been
busy in devising and developing new methods and techniques in place old ones for dealing
with social problems. In order to make research results more definite and precise, the use of
quantitative or statistical methods is increasing day-by-day. In this connection, it is said that
social scientist are professionals trouble makers; they must challenge old briefs create new
ones and then turn to the challenge on these new once.
1. 2 Types of Research
Methods of research may be classified from many points of views
 Application: pure research or applied research
 Character of data :- objectives, Subjective, quantitative or qualitative
 Field of application: social science, education, philosophy,, etc
 Purpose:- reporting description, explanation, or predication
 Forms of reasoning: - inductive, deductive, or combination of the two.
 Place where it is conducted:- the laboratory or in the social setting
 Extent of control of factors:- controlled or uncontrolled experiments
 Techniques of data gathering :-tests, observations, or questioning
The two type of research that deserve description at this point are Basic Research and
Applied research.
1.2.1 Basic Research
Basic research that is sometimes known as “pure research “or “fundamental research” has as
its main purpose the disclosure of its fundamental truths or principles. It is usually sent
7
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
towards the testing and development of theory and are not immediately concerned with direct
application. Thus in basic research control and precision are emphasized while less attention
is paid to direct application of the outcomes in field situation. Basic research in the business
arena might involve a researcher for an advertising agency who is studying the results of the
use of coupons versus rebates (discounts) as demand stimulation tactics, but not in a specific
instance or in relation to a specific client’s product. It is usually conducted to develop
theories, principles, and laws that are found in different subjects (areas) and helps to extend
the frontiers of knowledge.
1.2.2 Applied Research
Applied research or filed research deals mainly with determining relationships and testing
theories in the field situation. Because transfer of the research out - come directly to a field
practical is often the purpose of applied research; control and precision must be sacrificed to
a certain degree in order to conduct the study in a situation identical to that in which the
outcomes will be applied. Applied research may be
directed at the testing of theoretical
constructs.
1.3 Is Research Always Problem – Solving Based?
Of course, research is always problem based. Both types of research should provide an
answer to some questions.
Applied research has a practical problem solving emphasis. The problem – Solving nature of
applied research means it is conducted to reveal answers to specific questions related to
action, performance, or policy needs.
Pure or basic research is also problem solving based, but in a different sense. It aims to solve
perplexing (puzzeling) problems or questions of a theoretical nature that have little direct
impact on action, performance, or policy decisions. It is used to understand natural
phenomenon, but not to solve problems directly and immediately.
Thus, both applied research and pure research are problem based, but applied research is
directed much more to making decisions.
8
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
1.4 What is A Good Research?
A good research involves the following characteristics:
a) Purpose clearly defined,
b) Research process detailed,
c) Research design thoroughly planned,
d) High ethical standards applied,
e) Limitations frankly revealed,
f) Adequate analysis for decision makers needs,
g) Findings presented unambiguously,
h) Conclusions Justified.
Characteristics
What a manager should show look for in research
Purpose Clearly defined
Researches distinguish between organizations problems
systems and the research problem
Research process detailed
Research
design
Research provides complete research problem
thoroughly Research procedures (exploratory, descriptive, or casual)
planned
are outlined with constructs defined, sample units is
clearly described; data collection procedures are selected
and designed.
Limitations frankly revealed
Desired procedure is compared with actual procedure;
desired sample is compared actual samples impacts on
findings and conclusions are detailed.
High ethical standards applied
Safe guards are in place to protect study participants,
organizations, clients, and researchers.
Adequate analysis for decisions Sufficiently detailed findings are tied to collection
makers needs
instruments and the analysis is fact data based
Unambiguous finding
Finding is clearly presented in words, tables and graphs
are logically organized to facilitate reaching a decision
about the mangers problem.
Conclusion Justified
Decision based conclusion are matched with detailed
findings.
9
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
CHAPTER TWO
RESEARCH METHODS AND TECHNIQUES
 Classification of Research Methods
Different authors have given different classification of research methods in social science,
several methods are used. Any method based on scientific approach is suitable for social and
economic research but it must be carried out on a set pattern and its result should be reliable,
logical and certain.
Generally, under social and economic research importance is given to the following methods.
2.1 Historical Method
Any research which makes use of observations based on past events is known as research in
historical approach. The main aim of historical research is to apply the method of reflective
thinking to social and economic problems still unsolved by means of discovery of past trends
of events; facts and attitudes. It traces lines to development in human thought and action
intruder to reach some basis for social activity. Historical research method like all other
research methods is not merely concerned with collection of data and facts but editing
analysis, evaluation and interpretation of data are integral parts of it. The historical research
should conduct critical evaluation and interpretation of historical documents and records in
such a manner that general law, treads or hypothesis can be framed. Historical research is
essential for both basic and applied research in social sciences.
2.1.1 Definition
According to Walter R. Borg, “Historical Research is the systematic and synthesis objective
location, evaluation synthesis of evidence in order to establish facts and draw conclusions
concerning past events.
To quote Sheik Ali “Historical research is digging in to the past in order to re - enact the past
in its entirety to reconstruct the past events as fully as they have happened to explain the
meaning and significance of these events to correct the wrong notions so long prevalent, if
10
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
any, and to elaborate analyse, synthesise and philosophies the ideas in the light of the
knowledge we possess.
Robert G. Murdik says that “Historical research is concerned with establishing the
occurrence of unique events”. Although one phase of historical research consists only of
determining of past events the ultimate phase deals and present the establishment of pattern
of relation ships and the starting point of projecting trends”.
In the simple words, “Historical method seeks to find explanation of questions of current
interest by an intensive study of the past. Past always contains elements of the present. Past,
present and future are all well inter-linked. Infect every project of research has more or less
historical approach. In discussing any problem we must know the history of the problems and
only then the problem can be solved easily, quickly and accurately. To quote P.V. Young,
“The past, if it can be located, contains the key to the present, though today is different from
yesterday, it was shaped by yesterday. Today and yesterday will probably influence
tomorrow.
2.1.2
Significance of Historical Method
Historical research is useful both for theoretical and practical purposes. It has made important
contribution to various branches of natural as well as social sciences. Some problems are so
typical that they can only be investigated by this approach. Thus this method fills a gap of
making the research possible and meaningful and some problems other wise would have
remained unexplored with out it. Many a times it is of considerable interest to use time series
data for assessing the progress of the impact of several policies which can be done by looking
in to historical records only.
2.1.3
Sources of Historical Data
Generally, there are the following major sources of historical information before a social
researcher:

books and magazines

assessable documents, papers and literature

cultural and analytical history material

memories, personal letters and accounts
11
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)

personal sources of authentic observers and witnesses

diaries and confessions

autobiographies

scared archives

diplomatic agreements

statistical materials

Artistic materials, historical paintings, portraits, charts, maps, etc.
2.1.4 Advantages
The advantages of historical methods are
A.
Some problems are such which can be investigated only by this method and may not
offer other methods. Therefore, historical method fills in the big gap of making the
research possible and also meaningful on the problems that would otherwise have
remained unexplored.
B. Historical data is not repeatable under any circumstances and therefore, historical method
serves a needy hand method to the researchers whose problems depend on historical
observations. It is fairly easy to repeat observations in laboratories under controlled
conditions but can not be done in case of historical data. Historical method, therefore, has
an advantage to offer the past data under the then prevailing conditions and afford an
opportunity to the researcher to view these observations in the past setting.
C. Historical records provide very useful information that goes a long way towards the
solution of research problem. As already said the researcher is compelled to fall back up
on past data since he can to create these afresh and hence it is highly advantageous to
follow historical method where the use of time series data is unavoidable in any case.
2.1.5
Limitations
Historical method is not free from limitations. The main draw backs are:A.
Non-Matching situations
B. Over-generalization
C. Subjective Interpretations
12
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
Limitations may also arise in the writing of history itself because
(1) Historians can not write history life-sizes
(2) Not all happenings in time and space can be known at the time of writing
(3) Personal biases and private interpretations often enter unconsciously, even when
honest attempts are made to select pertinent facts, to arrange them consistently, and to
place them in a coherent and true frame of reference.
However, it should be observed that this approach can not be dispensed with as large number
of problems can not be investigated in the absence of historical research many times even
other approaches to research would desirably insight in to their own investigations.
Necessary conditions for Historical Research
i.
selection of topic for research
ii.
social in sight
iii.
Historical orientation
iv.
Knowledge of related social sciences
v.
Wide educational back ground
vi.
Familiarity with the topic and its objectives
vii.
Dispassionate study
viii.
Imaginative capacity
ix.
Selection and rejection of the material
x.
Analyzing and coordinating capacity
xi.
Knowledge of study field
xii.
Knowledge of his own limitations
xiii.
Availability of necessary facilities
2.1.6 Steps Involved in Historical research
The main steps involved in historical research are

Selection of the problem

Objectives of the study

Formulation of hypothesis

Preparations for collection of data
13
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)

Testing of hypothesis

Evaluation of data

Organization of data

Interpretation and writing report
2.2 The Case Study Method
A case study is deep and intensive study of a particular social unit, confined to a very small
number of cases. Thus the field of study in the case study method is limited but it aims at
studying all aspects of a social unit. It also seeks to determine social process; it reveals the
complexity of factors and indicates their sequences and their relationships. It is also a
diagnostic study oriented towards finding out what is happening and why it is happening and
what can be done about it. Case study says Charles H. Colley, “depends on our perception
and gives us a clear insight in to life”
2.2.1
Definition
Important definition of the case study method is
P.V young- “case study is method exploring and analyzing the life of a social unit, a
personal, a family, institution, cultural groups or even an entire community”
Goode and Hatt- “Case study is a way of organizing social data so as to preserve the unitary
character of the social object being studied. Expressed some what differently it is an
approach which views any social unit as a whole”
F.I. Whitney –“Case study is a complete analysis and report of the status of an individual
subject with respect as a rule to specific phase of his total personality”
2.2.2
-
Characteristics of Case Study Method
It places more emphasis on a full contextual analysis of fewer events or conditions and
their interrelations.
-
Although hypothesis is often used, the reliance on qualitative data makes support or
rejection more difficult.
-
An insight on detail provides valuable insight for problem solving, evaluation, and
strategy. This detail is secured from multiple sources of information. It allows evidence
to be verified and avoids missing data.
14
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
-
Although case studies have maligned (criticized) as “Scientifically worthless” because
they do not meet minimal design requirements for comparison, they none the less have a
significant scientific role. Thus, a single, well-designed case study can provide a major
challenge to a theory and can provide source of new hypothesis and constructs
simultaneously.
2.2.3
Advantages
The main advantages of case study method are it:
-
produces new ideas and fresh suggestions,
-
helps in formulating a sound hypothesis, and
-
may also help in exploring new areas of research
Since the case study method makes an in depth study of a particular unit of investigation and
is always approached with an open mind, it bestows upon the researcher further exploration
of the research field.
2.2.4
Limitations
Though the case study method has contributed much to the social research, some social
scientists have raised some objections against the value and validity of case study. The case
study method has often criticized on the basis of the following limitations.
 It develops false sense of confidence which is detrimental to any scientific out look.
Every thing about the subject can’t be known although each unit is studied.
 Generalizations about similar cases are impossible
 It does not provide universal, impersonal and common aspects of phenomena.
 It is quite unsystematic in the absence of any control up on the informant or the
researcher.
 Case study situations are seldom comparable
 It is difficult to apply the usual scientific methods without destroying the unique value of
the personal document will be lost if it is formalized and abstracted.
15
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
2.2.5
Basic Assumptions of the Case Study Method
A.
The case study method is not in it self a scientific basic at all, it is
merely a first step in scientific procedure.
B.
It is assumed that in the fact of apparent diversity among different units,
there is an underlying unit. A particular unit has its uniqueness. But it is
not different from other units in all respects.
C. Under this method it is assumed that a unit selected is the representative of a
group. In many respects it is similar to measures of central tendency or
averages. It tries to locate the variations in the reactions and activities of the
subject.
D.
It is also assumed that the study of a particular unit is helpful in the
prediction and discussion of other units of the same universe.
E.
A unit is indivisible whole and can not be studied piece-meal and in
fragments. We must study its life history and its back ground and to
explain the behavior at a particular time are few, but more.
2.2.6
Steps Involved in Case Study
A. selection of cases and identification of situations,
B. collection and recording of data,
C. interpretations of data,
D. report writing,
2.3 Survey Method
The term survey is used for the technique of investigation by a direct observation of a
phenomena or systematic gathering of data form population by applying personal contact,
and interviews when an adequate information about a certain problem is not available in
records, files and other sources. It is currently being used in those investigations also where
published data is used.
16
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
2.3.1
Definitions of Social Survey
Some of the important definitions of social survey are as follows: A.F Wells- “Social survey is fact-finding study dealing chiefly with working class,
poverty and with the nature and problems of community”.
 C.A. Moser- “The sociologists should look up on surveys as way and a supremely useful
one of exploring the field of collection data around as well as directly on the subject of the
study so that problem is brought in to focus and points worth studying are suggested”
 Mark Abrams- “A social survey is process by which quantitative facts are collected about
the social aspect of community’s composition and activities”.
 F.L. Whitney-“survey research is an organized attempt to analyze, interpret and report the
present status of social institution group or area.”
Survey method is, thus, the technique of investigation by direct observation of phenomena or
systematic gathering of data from population. Survey research is defined as an organized
attempt to analyze, interpret and the present status of social group.
2.3.2 Types of Surveys
The surveys may be classified with the following types:
A. General or Specific Surveys
A general survey is conducted for collecting general information of any population,
institution or phenomena without any hypothesis while specific surveys are conducted for
specific problems or for testing the validity of some theory or hypothesis.
B. Regular and Ad hoc Surveys
If the survey is repeated for regular intervals to obtain continuous information, it is known as
regular survey. It helps in the study trend of the effect of time on the phenomena under the
study for regular surveys a permanent machinery for collecting information has to be set up.
Ad hoc surveys are conducted once for all and are non-repetitive. Such surveys may also be
conducted in testing the hypothesis or supplementing some missing information regarding
any research problem.
17
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
C. Preliminary and Final Surveys
Preliminary survey is the plot study to get the first hand knowledge of the universe under
study. It helps the researcher in preparing schedule or questionnaire and organizing the
survey on proper lines. Final surveys are made after the pilot study has been completed.
D. Census and Sample Survey
Census survey deals with the investigation of entire population. Under this method the
information is collected from each and every unit of the universe. Money, material, time and
labour required for carrying out a census survey are bound to be extremely large but its
results are no more accurate and reliable. In case of sample survey only a small part of the
universe which is representative of the whole population is taken and the information is
collected. Thus the sample surveys are more economical and less time and labour consuming.
2.3.3 Advantages
Survey method has the following merits in comparison on with other methods:
 fosters direct close contact between researcher and respondents.
 greater objectivity – it avoids the possibility of personal biases.
 useful in testing the validity of many theories.
 proved its usefulness in leading to the formulation and testing of hypothesis.
 social surveys are based on actual observations.
 it has a universal application.
2.3.4 Limitations

Survey method is costly, time consuming and wasteful in certain cases where the
objectives are limited.

Unsuitable if the number of persons to be surveyed is very large or where they are spread
over a large geographical area.

Under this method personal bias may vitiate the result.

It lacks flexibility.

It is only useful for current problems and is not suitable for the problem that requires the
study in the historical retrospect.

Does not permit more comprehensive and dynamic study of the society.

Under this method most of the surveys are conducted on sample basis.
18
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
2.3.5 Steps of a Social Survey
a. Selection of a problem
b. Preliminary study or pilot study
c. General objective of the study and specific objectives
d. Resources and personnels
e. Sampling
f. Method of collecting data
g. Training the investigating staff
h. Organizing of the field work
i. Content analysis
j. Reporting
2.4 The Experimental Research Method
According to Festinger, “The essence of an experiment may be described as observing the
effect on a dependent variable of the manipulation of an independent variable.”
In the words of Greenwood, “An experiment is the proof of a hypothesis which seeks to look
up two factors in a casual relation ship through the study of contracting situations which have
been controlled on all factors except the one of interest the later being either the hypothetical
case or the hypothetical effect.”
According to V.H. Bedkar, “Experimental method implies a controlled observation of a
succession of events the aim is to search for casual connection”
This research method goes by various names, the experimental methods, the cause and effect
method, the pretest- post test control group design and the laboratory method. The basic idea
behind this method is to attempt to account for the influence of a factor or, as in the case of
complex designs, of multiple factors conditioning a given situation.
In its simplest form, the experimental method attempts to control the entire research
situation, except for certain input variables which then become suspect as the cause of what
ever change has taken place with in the investigation design. The experimental research
method requires us the understanding of different variables. But what are variables?
19
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
The term variable is used by scientists and researchers as a synonym for the property being
studied. In this context, a variable is “a symbol to which numerals or values are assigned.”
The numerical value assigned to a variable is based on the variable properties. For example,
referred to as being dichotomous, have only two values reflecting the presence or absence of
a property: employed- unemployed or male- female have two values. Variables can be seen
in to two categories:
2.4.1
Independent and Dependent Variables
A. Independent Variable
Independent variable is a variable that affects the value or characteristic of another variable
(the dependent variable). It can be manipulated or controlled by the researcher so that its
effect can be seen. Independent variables can also be classifying variables.
For example (1) in a study about the effect of assignment provision on the academic
achievement of students, the independent variable is assignment provision. The researcher
can control the situation of assignment provision. He/she may or may not provide assignment
to the subjects. So assignment provision is under the will of the researcher.
Consider the following example (2) a researcher wants to study about “Gender differences in
professional attitudes.”
What is the independent variable that can be varied by a researcher in the above example?
____________________________________________________________________
Have you identified it? Of course, it is gender. The researcher will take male and female and
compare their professional attitudes. In this case the independent variable is a classifying
variable.___________________________________________________________________
B. Dependent Variable
This is a variable being affected or assumed to be affected by the independent variable. It is
a measure of the effect of the independent variable. In the first example given above
academic achievement is the dependent variable.
What is the dependent variable in the second example? __________________________
Have you identified it? Yes, it is the professional attitude of the subjects.
Generally, if the investigator has control over the variable and is able to manipulate it or
change it at will, then we say that variable is an Independent variable. If, on the other hand,
20
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
the investigator has no control over the variable and it occurs as the result of the influence of
the independent variable, then the variable is known as the dependent variable.
The matter of control is central to the experimental method. We frequently refer to this
means for searching for truth as the control group, experimental group design. At the out set,
we assume that the forces and dynamics with in both groups are equisetic. We begin, as far
as possible with matched groups. These groups are randomly selected and paired so that,
each group will resemble the other in as many characteristics as possible and, certainly, with
respect to those qualities that are critical to the experiment.
Mathematically, Experimental group = control group
2.4.2
Characteristics of the Experimental Method
A. The experimental method deals with the phenomenon of cause and effect.
Thus, we have two situations and we assess each to establish comparability. We attempt to
alter one of these by introducing in to it an extraneous dynamic. We reevaluate each situation
after the intervening attempt at alteration. What ever change is noticed is presumed to have
been cause by the extraneous variable
B. Experimental research needs to be planned.
This planning is called the designing of the experiment. Experimental design refers to the
architectonics and planning of the entire experimental approach to a problem for research.
2.4.3 Advantages of Experimental Method
Main advantages of experimental method may be summarized as follows.

This approach is more rigorous. It has the advantage of scientific and vigor and
mathematical logic in so far as the entire piece of research work is based on a well
founded model.

In comparison to other methods, this approach permits the determination of cause and
effect relation ship more precisely and clearly.

Under identified conditions, a lot of it depends on the behavior of the respondents. A
respondent is always under the in thecae diverse social organism and it all depends on the
type of mental frame that he has at the time the researcher approaches him for
information.
21
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
2.4.4 Problems of Social Experiments
 Difficulty of co-operation
 Difficulty of setting
 Difficulty of control
 Errors of Measurement
2.5 Other Methods
2.5.1 Field Investigation Research
A field experiment is a research study in realistic situation in which one or more independent
variables are manipulated by the experimenter under as carefully controlled conditioned as
the situations will permit. Where the laboratory experiment has a maximum of control, most
field studies must operate with less control a factor that is often a severe handicap to the
experiment. The weakness of field experiment, therefore, is of practical nature. The control
can not be held as very tight, the investigator himself works under several influences and
may at times be faced with unpleasant situations and the independent variables may got
affected by uncontrolled environmental influences.
A field experiment is generally credited with a few virtues which are supposed to be unique
to this category of a research. This virtues may be listed as: (1) the variables in a field
experiment. This is because of the fact that field situation takes stock of realistic natural
operations. (2) field experiments have the advantage of investigating more fruitfully the
dynamics of inter- relationships of small groups of variables. (3) Field experimental studies
are as so ideal to testing of the theory and the solution of the real world problems.
2.5.2 Ex-post facto Research
This is an empirical research and the researcher does not have any control over independent
variables, because they have already been manifested. Ex-post facto researches systematic
empirical inquiry in which the scientist does not have direct control of independent variables
because their manifestations have already occurred or because they are in hearth not
manipulability.
22
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
Inferences about relations among variables are made, with out direct intervention, from
concomitant variation of independent are dependent variables.
This kind of research is based on a scientific and analytical examination of dependent and
independent variables- Independent variables are studied in retrospect for seeking possible
and plausible relations and the likely effects that the changes in independent variables,
produce on a single or a set of dependent variables.
In es-post facto research, the researcher’s control on the behavior of independent variables is
very weak and in many cases no control is possible.
Some of the weaknesses of ex-post facto research are summarized here under.
 The inability to control the charging patterns of independent variables.
 The ex-post facto research findings owe the risk of improper interpretations
 The ex-post facto research may not have any particular hypothesis as there is a likely
hood that such an hypothesis may predict a spurious relationship between independent
and dependent variables.
2.5.3
Laboratory Research
By definition, research of this type is confined to lab. Experiments alone. The basic feature of
such research is that there exists a possibility of exercising control over independent
variables and isolating their influences for plausible explanations.
A laboratory experiment is a research study in which the variance of all or nearly all of the
possible influential independent variables not pertinent to the immediate problem of the
investigation is kept at a minimum.
This is done by isolating the research in a physical situation apart from the or ordinary living
and by manipulating one or more independent variables under rigorously specified,
operational zed and controlled conditions.
This type of research has a limited application in social sciences as it extremely difficult to
study social variables in isolation of each other.
23
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
However, it may, at times be possible to create a situation; where in a maximum control can
be exercised to keep the variations among the independent variables at a maximum. In such
cases laboratory experiment types of research may find its applicability in social research as
well.
2.5.4 Action Research
This is a recent classification. This type of research is conducted through direct action. The
actual study may consist of a number of phases, say, base-line survey, systematic action,
periodical assessment, etc. A good example of action research is a study of test marketing. A
base line survey is initially conducted and the informants are identified; and this is followed
by the distribution of the product under study, and then an assessment of survey.
It is very useful method in consumer product. Even in the case of industrial products,
machinery and consumer durables, the action research method is used when, instead of
distributing the product, demonstration is made as part of action research. Action research is
also termed as applied research because it is a type of research that will be conducted to solve
immediate practical problem(s). By its very definition, it is research through launching of a
direct action with the objective of obtaining workable solutions to the given problems.
In conducting research through launching of actions, this type of research has the quality of
adapting itself to the changes take place in a given population. Action research is spread over
different phases such as a base line survey, where all the possible information of research
interest is collected to enable the researcher to acquaint him self with the existing operational
situations. This also aims at collecting information from the other sources that have direct or
planned action is particularly launched and then at the next phase action research carries out
periodical assessment of the project.
At subsequent stage, changes, modifications and other improvements are made in the
functional aspect of the project and finally the whole process culminates in the evaluation of
the project as a whole.
The method used for this type of research is usually personal interviews method and the
survey method. Some times attitude measurement techniques are also made use of some
24
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
problems associated with action research are the personal values of the personal values of the
individuals, lack of social scientists interest and exclusion locations with the respondent.
Generally, action research is directed to the solution of immediate, specific and practical
problems. The findings of action/ applied research will be evaluated in terms of local
applicability and not in terms of universal validity (usefulness). It is mainly intended to
improve certain contextual problem and helps to add greater effectiveness in a certain
practical manner. It focuses on the solution of day-to- day problems at the local level.
25
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
CHAPTER THREE
FORMULATION OF RESEARCH PROBLEM AND
HYPOTHESIS
3.1 Research Problem
One of the most difficult phases of any research project is the choice of a suitable problem.
The beginner is likely to take a very long time in making his choice. In this first step of any
research the research worker should not take a hasty decision. Every problem, which comes
to his mind or even that suggested by a more experienced person, may not be a fit research
problem. The identification of a good research problem should be considered a discovery in
it self.
Identification of a research problem is the first step in scientific inquiry. A problem in simple
words is some difficulty experienced by the researcher in a theoretical or practical situation
solving this difficulty is the task of research.
The problem defines the goal of the researcher in clear terms. Thus, with out a problem,
research can not proceed because there is nothing to processed from and proceed toward. In
social sciences, quite a number of researchers may be faced with this problem, i.e., the
problem of not being able to see a problem.
Personal values play an important role in the selection of a topic for research. Social
scientists with different values tend to choose different topic for investigation. Of course,
personal values are not the only determinants in selecting a topic for inquiry. Social
conditions do often shape the preference of investigators in a subtle and imperceptible way.
There are also a number of powerful and overt inducements to selection of one topic rather
than another. Societies differ in respect of premium they place on the work in different fields.
These differential premia affect the choice of research topics. In a given society, it may bring
greater prestige to do research on a deadly disease rather than on say, the patterns of
socialization.
The selection of a topic for research is only half a step forward.
26
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
3.1.1
How to Proceed?
The formulation of the problem consists in making various components of the problem
explicit.
Says John Dewey: It is a familiar and significant saying that a problem well put is halfsolved. To find out what the problem or problems are which a problematic situation
presents…. Is to be well along in inquiry. To mistake the problem involved is to cause
subsequent enquiry to be irrelevant. With out a problem there is blind grouping in the dark.
There are three principle components in the formulation of a problem.
A. The originating questions (what one wants to know?)
B. The rational- theoretical or practical (why one wants to have the questions answered?)
C. The specifying questions (possible answers to the originating) questions in term of that
satisfy the rationale.)
A. The Originating Questions
-
Represent the beginning of certain difficulties or challenges
-
Are formulated in such specific indicate where exactly the answers to them can be
searched for.
-
Constitute the initial phase in the process of problem formulation.
-
May be formulated in terms of broadly delimited categories of social variable but do
not indicate specifically which particular variables in each class might be germane to
the issues.
-
Usually derive from a general theoretical orientation rather than a definite theory.
B. Rationale of Questions
- Is the statement of reasons why a particular question is worth putting a cross .
- States what will happen to other parts of knowledge or practice if the question
posed is answered, i.e., how the answer to the question will contribute to theory
and/ or practice.
- Helps to effect a discrimination between scientifically good and scientifically
trivial questions.
27
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
C. Specifying Questions
o Culminate the process of formulating a research problem
o Involve the breaking down of originating question in to several specifying questions
related to particular aspects and their consequences.
3.1.2 Necessary Conditions for Formulating a Research Problem
We may now list some of the conditions that experience has proved to be conducive to
formulation of significant research problems.
A. Systematic Immersion in the Subject matter through first hand observation
The researcher must immerse him/her self in the subject – matter area with I which he/ she
wishes to pose specific problem. This exercise helps a great deal in suggesting to the
researcher the specific questions that may be posed for the study to answer. This process is
know as pilot survey, preliminary survey or exploratory study.
B. Study of Relevant Literature on the Subject.
This would help the researcher to know if there are certain gaps in the theories (his/her
research will then be to bridge this gap) or whether the prevailing theories applicable to the
problem are in consistent with theoretical expectations and so on. This is also an aspect of
exploration.
C. Discussions with persons having rich practical experience in the filed of study.
This is often known as an experience survey, which again is an exercise at exploration. These
people help in sharpening the focus of attention on specific aspects with in the field.
3.1.3 Sources of Research Problem
The research problem may be selected from the following sources:
 theory of ones own interest ;
 daily problems;
 technological changes;
 un explored areas; and
 discussions with other people
28
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
A research may select a problem for investigation from a given theory in which he has
considerable interest. In such situations the researcher must have thorough knowledge of that
theory and should be sufficiently inquisitive to explore some unexplained aspects or
assumptions of that theory.
Research problem can also be selected on the basis of daily experience of a researcher.
Everyday problems constantly present something new and worthy of investigation and it
depends on the worthy of investigation and it depends on the sharpness of the researcher
intellect to knit his daily experiences in to a research problem.
Technological changes in a fast changing society are constantly brought forth new problems
and new opportunities for research. What is the impact of a changed technology on the
existing socio – economic set up, always interests the researcher and tempts him to under
take such studies as are revealing regarding the impact of new technology on the existing
system.
Research problems can be both abstract and of applied interest. These may also be selected
from those areas which have not been explored so far. Such area may be theoretical or
empirical in nature.
Some times the researcher while discussing the interest with some other people may come
across a problem that can be researched by the investigator. The problem may relate to any
source as discussed above. In the same way reading assignments in text books, special
assignments, research reports and term papers may also suggest some additional areas of
needed research. Many research articles suggest some additional areas of needed research.
Many research articles suggest problem for further investigation that may prove fruitful.
3.1.4 Criteria of a Good Research Problem
Factors to be taken in to account in the choice of research problem are both external and
personal. External criteria involve such issues as newness and significance for the area,
availability of data and method and administrative and institutional cooperation personal
criteria include such consideration as interest, training, cost and time. The following are
move detailed list of criteria for the choice of research problem.
29
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
A. Novelity
It should be sufficiently original so that it does not involve objectionable duplication.
Ignorance of prior studies may lead a student to spend time a problem already investigated.
The study should also employ the most recent data. Although originality is an important
consideration, there is also a constant need for verification of the findings of the previous
investigations, using newer and better devices and procedures. There is also a need for the
testing of former findings under changed conditions.
B. Interesting
The problem should be interesting for the investigator him self. If he is not interested in to,
he will be able to face and overcome the obstacles which come at every step in research. His
interest should be purely intellectual and should not be there only for a reward, material
benefit, advancement in position, increased authority, etc.
C. Importance
If it is not worth while, if adds to neither knowledge nor lead to any improvements in the
current practices, it would be in vain set up as a discipline and to previous research findings
in any way.
D. Immediate Application
The investigator should ask him self question, “will my research help in solving an urgent
problem”
E. Feasibility or Amenability
The suitability of the problem for a particular research worker is the matter of its feasibility.
The investigator should be able to carry it to a successful conclusion. He should possess the
required competence, knowledge and understanding. He should be skillful enough to
develop, administer, and interpret the necessary data – gathering devices and procedures etc.
Feasibility issue of research includes the following
 Availability of data
 Availability of cooperation
 Availability of guidance
 Availability of other facilitates
 Experience and creativity,
 Coverage and confidence
30
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
3.1.5 Formulating and Stating the Problem
After the problem has been selected it must be definitely formulated and stated in precise
terms. The type of statement to be employed depends on the preference of the worker and the
nature of the problem.
There are two alternative ways of stating a problem.
 Posing question (s)
 Making declaration statement (s)
One may choose any of these ways remembering that the question form has an advantage in
sharpening and focusing the issue, but the declarative form is perhaps more common and
both of the ways may be combined easily in an initial statement .
3.1.6 Definition of the Problem
It implies the separation of the problem from the complex of difficulties and needs. It means
to put a fence around it, to separate it by careful distinction from like questions found in
related situations of need.
To decline a problem means to specify it in detail and with precesion. Each question and
subordinate question to be answered is to be specified. Sometimes it is necessary to
formulate the point of view or educational theory on which the investigation is to be based. If
certain assumption is made they are explicitly noted.
It is important to define and elucidate the problem as a whole and further define all the
technical and unusual terms employed in the statement.
3.1.7
Common Errors in Formulating Research Problem
A. Naming a Broad Filed
To choose the broad area of study instead of specific problem makes no justification .
B. Narrowing or Localizing a Topic
The problem should not be narrowed to such an extent that it becomes too small and
insignificant from research point or view.
31
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
C. Lock of Precisions in the Instrument
It the tools, tests, or devices, which are proposed to be used in data collection and analysis
are no precise enough, they may result in another constant error.
3.2 Hypothesis
The derivation of a suitable hypothesis goes hand in hand with the selection of a research
problem.
Hypothesis is a statement temporarily accepted as true in the light of what is, at the time,
known about the phenomenon, and it is employed as a basis for action in the search of new
truth.
A hypothesis is a tentative assumption drawn from knowledge and theory which is used as a
guide in the investigation of other facts and theories that are yet unknown.
It is a guide, supposition or tentative inference as to the existence of some fact condition or
relationship relative to some phenomenon which serves to explain such facts as ready are
know to exist in a given area of research and to guide the search for new truth.
A hypothesis is a tentative supposition or provisional guss which seems to explain the
situation under observation.
A hypothesis states what we are looking for. A hypothesis looks forward. It is a proposition
which can be put to a test to determine its validity.
3.2.1. Importance of Hypothesis
A. It provides direction to research. It defines what is relevant and what is irrelevant.
Thus it prevents the review or irrelevant literature and the collection useless or
excess data.
B. It sensitizes the investigator to certain aspects of situations which are relevant from
the stand point of the problem in hand. It spells the difference between precision and
haphazardness, between fruitful and fruitless research.
C. It. Is a guide to thinking process and the process of discovery. It is the
investigators eye – a sort of guiding light in the world of darkness.
32
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
D. It focuses research with out it research would be like a random and aimless
wandering.
E. It places clear and specific goals before us. These clear and specific goals provide
the investigator with a basis for selecting samples and research procedures to
meet these goals.
3.2.2 Characteristics of a Usable Hypothesis
The criteria for judging the usability of the hypothesis are non else than those that help the
hypothesis perform their designated functions vis- a – vis research and the growth of
knowledge. Hence, a “good” useable hypothesis is the one which satisfies many of the
following criteria.
- A hypothesis should be empirically testable
-A good hypothesis in agreement with the observed facts.
-A good hypothesis does not conflict with any law of nature which is know to be true.
-A good hypothesis is expert.
-It should be so designed that its test will provide an answer to original problems which
forms primary purpose of the investigation.
-It must be stated in final form early in the experiment before any attempt at verification
is made.
-The hypothesis must be conceptually clear.
-The hypothesis must be specific
-Advisedly, the hypothesis should be related to a body of theory or some theoretical
orientation.
3.2.3
Difficulties in the Formulation of Hypothesis
-Lack of knowledge and clarity of the theoretical frame work of the area in which the
investigator chooses to work.
-Lack of ability to make use of the theoretical frame work logically.
-Lack of acquaintance with available research techniques. This result in failure of
phrasing the hypothesis properly.
-Vagueness of the statement
33
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
CHAPTER FOUR
THE RESEARCH PROPSAL
Research proposal is a written document of the research topic chosen and why, a plan of
future research and an explanation of how it will be achieved. The document is prepared for
both requesting authorization and funds to under take a specific research project. It is an
activity that incorporates decision made during early research – project planning phases of
the study including management – research question hierarchy and exploration. The proposal
thus incorporates the choices the investigator makes in the preliminary steps.
It systematically outlines the particular research methodology and details the process that will
be utilized at each stage of the research process.
A written proposal is often required when a study is being suggested. It ensures that the
parties concur on the projects purpose and on the proposal method of investigations.
Depending on the needs and desires of the investigator, substantial background detail and
elaboration of proposal techniques may be included.
It is also the road map of the research which reveals about the what, who, who, why, how of
the research project.
4.1 Basic Functions of a Research Proposal
A research proposal serves:
4.1.1 As a Means of Communication
It serves to communicate the investigators plan to those who gives consultations and /or
disburse fund.
4.1.2 As a Plan
It helps the researcher to organize his idea in a systematic manner and look for strength and
flows. A good proposal set out the plan in step by step detail and provides an inventory of
what must be done and which materials have to be collected as preliminary step.
34
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
4.1.3 As a Contract
A complete proposal approved for execution and signed by all parties constitutes a bound of
agreement between the parties.
The length and complexity of research proposals range widely. Business research proposal
normally range from one to ten pages. Applicants for foundation or government research
grants typically file a proposal request of a few pages, often in standardized format specified
by the granting agency. A research proposal may also be oral, where all aspects of the
research are discussed but not codified writing. This is more when a manager directs his own
research.
4.2 Characteristics of a Good Research Proposal
More than any other factor, research demands that those who undertake it be able to think
without confusion clearly. The proposal will demonstrate whether you possess that quality.
Your reputation as a researcher more often than not rest squarely up on the quality of the
proposal you submit. It is well, therefore, to appreciate exactly what characteristics a
proposal should have.
1. A proposal is a straight forward document. What ever does not contribute directly to the
delimitation of the problem and its solution must be eliminated. Remember the a
architects drawing: Clean, Clear and economical. It contains all that is necessary; not one
details more.
2. A proposal is not a literally production. An architect drawing is not a work of art: A
proposal is not a “literally” production. The mission of neither is to be artistic; the
purpose of both as to communicate clearly. It provides no opportunity for fine writing, for
literary composition, for verbal extravagance. The language must be clear, precise, and
sharp, A proposal provides a chance to show with what ultimate clarity and precision the
researcher can state a problem, delineate the treatment of the data, and establish the
logical validity of a conclusion.
35
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
Further more, Objectivity, reliability, Validity are considered as characteristics elements of a
good research design.
4.2.1 Objectivity
The objectivity of the findings pertains to the methods of collection of data and scoring of
the responses. The objectivity of the procedure (either collection of data or scoring of the
response or both) may be judged by the degree agreement between the final scores assigned
to different individuals by more that one independent observer. The more “subjective” the
observation, recording and evaluation of the responses, the less different observes agree.
Thus any research design should permit the use of measuring instruments which are fairly
objective in which every observer or judge seeing a performance arrives at precisely the same
report. This ensures the objectivity of the collected data which will be used for the analysis,
inferences and generalizations.
4.2.2 Reliability
Reliability refers to “consistency thorough out series of measurements. That is to say, if a
respondent gives out a response to a particular item, he is expected to gives the same
response tot hat item when ever he is asked subsequently. On the contrary, if the respondent
keeps on changing his response to the same item when he is asked repeatedly, then the
investigator will be facing a difficulty in considering which one of these responses is the
genuine response of the respondent. So the investigator should frame his item in such a way
that the respondent can not but give only one genuine response. There are different methods
in determining the reliability of the response give out by a respondent. Some of these
methods are using ‘chick item’ administering the same test repeatedly; using a series of
‘parallel’ forms etc.
4.2.3 Validity
Any measuring instrument is said to be valid when it measures what it purports to measure.
For example, an intelligence test, constructed for measuring intelligence should measure only
intelligence and noting else. As in the case of reliability there are a good number of
procedures for establishing the validity of test. Some such procedures are validating the
present data against a concurrent, criterion of a future criterion or theory etc.
36
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
4.3 General Formulation and Elements of the Research Proposal
There is no hard and fast format in specific research proposal writing. It varies from
organization to organization and the complexity and nature of the research.
Proposal follows a simple, logical form of presentation. Although there are many ways to
arrange the items with in the proposal, the following serves as a check list of items in your
writing a proposal. Though format varies, the essence expressed in the different formats
remains the same.
4.3.1 The Preliminaries
A. Title
The title, which reflects the research under consideration, must be chosen based on the
criteria the relevance it has, the feasibility of undertaking the study, the applicability of the
research result, and the cost effectiveness.
The title should:
-Be clear, short, and transparent
-Capture and reflect the content of the proposal. It should enable the readers to
understand the concepts of the study.
Title may sometimes be too short to be clear for instance, the title’ Credit and Poverty’ may
suffice as a text book title but it needs to be explicit and say more if it is to serve usefully as a
research title. On the other hand, title may be too long to be readily and easily compressible.
Excessive length in titles is often attributable to ‘waste’ or fat words such as ‘an investigation
on …’ or ‘studies to example….’and the use of the words that should appear in the main text.
B. Kinds of title
I. Inductive Title
This type of title states the subject of the research (proposal) rather than the expected out
come.
Eg. ‘The role of agricultural credit in alleviating poverty in low-Potential Areas of Ethiopia’
II. Hanging title
The hanging title has two parts a general first part followed by a more specific second part. It
is useful in rewording another wise long, clumsy and complicated indicative title.
37
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
E.g ‘Alleviation of Poverty in low-Potential Areas of Ethiopia: the impact of Agricultural
Credit’
III. Question Title
Question title is used less than indicative and hanging titles. It is, however acceptable where
it is possible to use few words – say less than is words.
E.g ‘Does Agricultural Credit Alleviate Poverty in low- Potential Areas of Ethiopia?
C. Abstract
An abstract is known by different names like executive summary, synopsis, and epitome. It
gives executives the chance to grasp the essentials of the proposal with out having to read the
details. It should also include a brief statement of the problem, the research objectives/
research question (s) and the benefits of your approach.
It is the section which reflects the whole content of the proposal. It should be concise,
informative and should provide brief information on about the whole problem to be
investigated.
An effective abstract should present highlight, of the main aspects of the proposal concisely
and clearly. A good informative abstract starts by stating the problem to be solved through
the purpose, expected outcomes, beneficiaries, expected impact of the work being proposed
and the method to be used.
4.3.2 The Body Parts
A. Statement of the Problem
The problem statement contains the need for the research project. The problem is usually
represented by a management question or originating question. This problem is usually
represented by a management question. It is followed by a more detailed set of objectives.
Once the investigator is able to collect different studies conducted in his field of investigation
from various source and examine each one of them critically for the points mentioned above,
he will be in a position to state his problem in unambiguous and more precise terms. Usually,
the problem of investigation is stated in two ways – (a) in the form of a statement or (b) in
38
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
question form. In some cases the problem is stated with the help of more than one statement
or question.
Thus, in this part of your work, you have to explain what the problem is all about. Problem
statement must do better than produce merely a splutter of wordy and meaningless fragments.
Accordingly, it you know the problem, state it clearly. Each word of the problem should be
expressive, sharp, indispensable and definitive. Always state the problem in a compute
grammatical sentence. Your problem should be stated so well, infect that any one (who
understand English) could read it and react to if with out benefit of your presence If, for any
reason, your problem is not stated with such clarity, then you are merely deciving your self
that you, yourself know what the problem is such deception will merely cause you trouble
later on.
Clarity in statement of the problem is import ant for the following three basic reasons
i, It is the foundation for the development of research problems which aare necessary for
securing funds.
ii, It enables the researcher to describe the problem practically, to think about its importance,
its priority and to point out all the necessary points
iii. It provides the research with the basis for discussion with people in the community, the
relevant government \agency, and /or the potential funding agency.
As a general rule in research proposal writing, the other possible approach is to have an
introduction section which discusses the background of the problem followed by a problem
statement or rationale (can be separate section) discussing the need for undertaking the study.
A statement of the problem or description of the background of the study topic is the first
major section of the research proposal.
B. Research Objectives (Objectives of the Study)
The investigator will spell out the objectives of the present study in the form of statement and
while doing so, he takes care that the objectives mentioned are well with in the scope of the
investigation envisaged by him.
39
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
Recall that the research question can be further broken down in the investigative questions. If
the proposal is for a descriptive or casual study, then the objectives can be restated as a
hypothesis.
The objective flows naturally from the problem statement, giving the sponsor specific,
concrete, and research proposal must be SMART (Specific Measurable, Achievable,
Realistic and Time- bound). It is best to list the objective either in order of importance or in
general terms first, moving to specific term (i.e, research question followed by underlying
investigative questions). The general objectives of a research provide a short statement of the
specific goal being pursued by the researcher. The research questions (or hypothesis, if
appropriate) should be set off from the flow of the text so they can be found easily. The
specific objectives are operational in nature.
1. They should be stated in a form which shows the relations between variables
2. Must clearly state the target of the research activity, i.e, what kind of results are expected
or sought from conducting the research.
The research objectives section is the basis for judging the remainder of the proposal and,
ultimately the final report. Verify the consistency of the proposal by checking to see that each
objective is discussed in the research design, data analysis, and results sections.
C. Significance of the study
In this section, the researcher indicates the importance of the research and there by convinces
the reader. The researcher is, thus, required to indicate what his research will contribute
whether the research is to provide solution or to shed light on the nature of the problem or
both. Some researches extend the frontier of knowledge. This section, therefore, enable the
researcher questions like.
 What is the usefulness of this study?
 What does this study contribute?
Also, if the particular study is exploratory in nature, its importance to serve as an input for a
further detailed study will be stated.
40
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
The significance of the study is usually stated as follows. The purpose of the research is to:
 shed the light on the nature of the problem
 give solutions to the problem
 extend the frontiers of knowledge
 enrich the literature
D. Delimitations of the Study
This part indicates the scope – coverage-of the study. Your study should be delimited to a
manageable size. This should be done in relation to the area coverage as well as to the extent
of treatment of the variables in your study.
In this section you (as a researcher) indicate the boundary of the study. The problem should
be reduced to a handy (manageable) way. The rule is “Don’t bite more than what you can
chew”. The motto of the researcher is “this one thing I do; this one area I investigate; this one
question I attempt to answer, this one problem I am to solve.”
Delimitation is done to solve the problem using the available financial, labor and time
resources. This does not, however, mean that we should delimit the research topic to
particular issue and/ or organization or place because it is less costly and take less time.
Delimitation is done not to necessarily reduce the scope of the study for the sake of
minimizing the effort to be exerted. This means that we should not sniff the life of the topic
in the name of making it manageable. Thus, there should be a balance between manageability
and representativeness of the universe being studied.
E. Limitations of the Study
This is a part that you will include some constraints or difficulties you think that they have
influence on the weaknesses in the methodology , lack of access to data, faulty instruments,
sampling restriction, lack of recent literature in the area, financial constraints, lack of
cooperation, time, constraints and others.
Generally, limitations are difficulties the researcher faced during doing the research. Even
though the researcher designs and plans his study carefully, there could still be certain
constraints that might hinder the researcher from doing the research as it should be.
41
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
This is usually written after the work is completed because it is known only then. Thus, it is
not usually indicated in the proposal However, it is possible to indicate limitations expected
and solutions envisaged.
F. Definition of Used Terminologies
It is importance to give meanings of different terms used in the investigation. The researcher
should be clear about the meanings of every term he uses. It not only helps him but also the
other investigators, respondents and readers of the research report in understanding the
different terms with out any ambiguity. Normally these concepts are explained either in the
form of nominal definition or in the form of operational definitions.
Nominal definitions are used in cases where a given word is synonymous with certain other
expressions, the meanings of which are already established.
Operational definition: a variable or a concepts is said to be operationally defined when the
steps in its observation or measurement are clearly stated. Thus an operational definition of
concepts helps the investigator in obtaining reliable results, with out which he can not
establish any fact scientifically which in its turn makes the problem of investigator much
more complex in his attempt to accept or refuse the hypothesis under consideration with
more authenticity.
Sometimes, the investigators even define a variable operationally with the help of items in
the questionnaire or interview schedule.
The investigator usually engager himself in the following exercises before arriving at the
operational definitions of the different terms.
The investigator will:(a) discover the various dimensions involved with in the concept, (b)
correlate these different dimensions so that all possible types can be discerned, (c) reduce the
number of types to be studied, (d) translate those types selected for study in to operational
categories and empirical indices.
It is always advisable to define each concept both: (i) in abstract terms giving the general
meaning it intends to convey, and (ii) in terms of operational categories by which it is
represented in particular study.
42
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
G. Review of the Related Literature
Literature review means
-Locating literature from a variety of resources
-Reading if Carefully and thoroughly, and
-Organizing it in to themes (ideas) along the line of investigation.
This section examines recent (historically significant) research studies, company data or
reports, book, magazines, and other written documents that act as a basis for the related
literature and relevant secondary data from a comprehensive perspective, moving to more
specific studies that are associated with your problem. If the problem has a historical
background, begin with the earliest references.
It is recommended that you should avoid the extraneous detail of the literature by doing a
brief review of the information, not a comprehensive report. Emphasize the important results
and conclusions of other studies, the relevant data and trends from previous research, and
particular methods or designs that could be duplicated or should be avoided. Discuss how the
literature applies to the study you are proposing; show the weakness or faults in the design,
discussing how you would avoid similar problems. Close the literature section by
summarizing the important aspects of the literature and interpreting them in terms of your
problem.
The review of related literature should give readers the context for the present study. The
review should not merely summarize a series of books and articles; rather, it should call
attention to the most important previous work, identify the place of your study in relation to
other research, and delineate areas of agreement and disagreement in the field. The review
should evaluate and interpret existing research rather than simply repeat it. Organizing the
review by topic rather than by author and avoiding un necessary direct questions can help
you focus the review of research.
I. The Major Purpose and Importance of Literature Review
In a research undertaking, your own research problem is always central. Everything that you
do, you do because it aids and assists you in attacking your problem. And when you know
what others have done, you are better prepared to attack with deeper insight and more
43
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
complete knowledge the problem you have chosen to investigate. But this is only the
principle reason for investigating the literature. Briefly such a review can provide you with
many benefits
a. It can reveal investigations germane to your own, and it can show you how the collateral
researcher handled those issues.
b. It can suggest a method or a technique of dealing with problematic situations, which may
also suggest avenues of approach to the solution of similar difficulties you may be facing.
c. It can reveal to you sources of data, which you may not have know existed.
d. It can introduce you to significant research personalities of whose research effort and
collateral writings you may have had no knowledge..
e. It can help you to see your own study in historical and associational perspective and in
relation to earlier and more primitive attacks on the same problem.
f. It can provide you with new ideas and approaches, which may not have occurred to you
g. It can assist you in evaluating your own research effort, by comparing them with related
effort, done by other.
II.
Guidelines to Begin a Search for Related Literature
 Go to the indexes and abstracts, Bibliographies should not be over looked. Perhaps one of
the best current sources in the bibliographic index.
 Go to the library armed with data gathering tools. You will need bibliography cards and
container to carry them in. Bibliography cards are valuable to gather and record
information. It also helps in locating it again with out continual return trips to the library.
 Make as many copies of the bibliographic items as necessary.
 Be systematic and thorough “make haste slowly” is a sound rule for the researcher. It
would be much better to take the required care and to give proper attention to doing the
job right in the first place.
 Relate your bibliography to your problem.
 The competent researcher never forgets that everything be does serves only one purpose
to contribute to the solution of the problem.
III.
How to Write to Section on the Related Literature
After they lave amassed an impressive bibliography, many students do not know what to do
with it. A few simple guidelines may help.
44
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
a. Review the Literature; do not Reproduce it
-
Present your own discussion,
-
Paraphrase, Precisely; give synopsis
-
Use short direst questions if necessary
-
Long direct questions are the last resort use them only for a very good reason.
b. Summarize What You have said
At the end of the presentation and processing of data in the research report, in the final
summary of the research, one question is always appropriate” What does it all mean?” one
heading is always in order the heading entitled, “summary.”
c. Get the Proper Psychological Orientation
Too many students consider the related literature as an unnecessary appendage standing in
the way of their goal. They are eager to get on with the research. To the contrary, a
conscientious and through review of the literature review related to the problem can open to
any researcher possibilities of which he was un aware, can open his eyes to new ways of
looking at the problem which he to tally missed.
d. Have a plan
Begin your discussion of the related literature from a comprehensive like as inverted pyramid
broad and first. Then you can deal with more and more specific or more localized studies
which focus closer and closer on your specific problem.
e. Emphasize relatedness
Emphasize relatedness keep your reader constantly aware of the manner in which the
literature you are discussing is related to your problem. Point out precisely what the
relationship is. When ever you cite a study, make your self account for that particular study
in terms of the problem you are researching.
f. Use proper Citation Style
Citation refers to indicating the source of borrowed or quoted idea “ Plagiarize” is defined as
to steal and pass off (the ideas or word of another) as ones owns to use(a created production )
with out crediting the source. The three ways one can be quality of plagiarism are
i. Paraphrasing some one else’s words at length with out giving
him/her credit
45
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
ii. Copying some one else’s word or sentence- verbatim with out
quoting appropriately and showing a reference.
iii. Using ideas that have been strongly influenced by some one else’s
work with out giving appropriate credit.
Paraphrasing is taking some one else’s word and putting it in to own word.
Quoting is copying taking some one else’s word or sentences variation. If the question
appears as part of a paragraph, it should be preceded and followed by quotes. If the quotation
is longer that four typed lines, it should be set off as a paragraph of its own, single spaced,
and typed with out quotation make. Both paraphrased and quoted materials should be
reference carefully.
H. Reference Styles
Three of the most commonly used referencing styles are the APA (American Psychological
Association), MLA (Modern Language Association of America), and Turbian (named for its
creator, kate L. Turbian) Styles. The APA style relies on in text mention of the author’s name
and year of publication.
Examples:
1. Grapevine communications are much more accurate than most people think. Typically,
75-85% of the information the grapevine carries is true. (Davis,1981)
2. Davis (1981) reports that grapevine communications are more accurate than most people
realize. Typically, 75-85% of the information the grapevine carries is true.
3. The underlining show the alternative referring styles. If the writer quotes Davis directly
as in the following except, then the page number might be added to the reference
“The degree of grapevine activity is a misuse of company’s spirit and vitality. If employees
are so disinterested in their work that they do not engage in shop talk, they are maladjusted.”
(Davis, 1973:45 )
The MLA style is similar to APA form of textural citation the main difference is that the
PAP will cite the authors’ name and date of publication, where as the MLA will provide the
authors last name, Title of work, and page numbers.
Example.
46
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
Universality of management suggests that the manger uses the same managerial skills and
principles in each managerial positions help in various organizations. (Dalton, “Business
management,”64)
What ever the writer chooses, he should be careful to maintain consistency. When the author
of the referenced material is two or three, the last name of each of the authors should be
indicated.
However, if the authors are more than three, only the name of the first author is written
followed by et.al., which means “ and other”, the abbreviation et. al. should be underlined as
it is Latin word written in English
Example
According to Thompson et.al., there is a general agreement that once a training program is
over we should try to check its effectiveness.
Under the Turbian style, each citation is given a number starting with 1 and proceeding
consecutively through the paper. The number are typed slightly above the line to distinguish
them from the text. Corresponding foot notes may be typed as endnotes or at the bottom of
the page. If typed at the end of the page, a line about 1 and ½ inches long should be typed to
separate the text from the footnotes. Here is an example of a reference and the accompaning
footnote using Turbian style.
Grapevine communications are much more accurate than most people think. Typically 1585% of the information the grapevine carries is true.3
Another style concern is how to repeat references, that is reference to sources that have been
cited and are now being cited again.4 consider the example that follows. The turbian using
the following Citations. 5
The notion Ibid is the abbreviation fort he lation ibidem, meaning “ in the same place”, It is
used when a repeated reference immediately follows the original reference.
In the case where other references come between the original and the repeated citation of a
given reference, the author’s last name and the latin op.cit. (Operacitato, in the work cited)
4 Gibson and Hdgetts, op.cit
47
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
The notation Loc.cit is the abbreviation for the Lafin loc citamus, meaning, the work cited
earlier the same place (page). When the page is the same, we use loc.cit and when the page is
different, we use op.cit
 Gibson and Hodgetts, loc. Cit
It is advisable, under the APA and MLP styles, to use the any reference list once under
“References” or Bibliography” and its location to determined alphabetically according to the
first author’s surname for foreign names. However, under the Turbian methods, as can
clearly be seen from the examples, the names are not transposed as in the case of
bibliographic presentation.
Moreover, in the case of bibliography, the first line of bibliographic entry starts from the left
margin and the subsequent lines of that entry are indented 10 spaces In the case of footnote
or end notes, however, is the first line of the reference that should be indented and the
subsequent lines start at the left margin.
In addition to indicating conations to acknowledge indebtedness and to determine the validity
of the evidence footnotes are used for the following purposes.
a, To elaborate the ideas or information presented in the text. If discussing some thing with in
the body is difficult (or not necessary), one can type the number slightly above the term (s)
to be explained at the foot of the page.
b, To give cross reference to different parts of the same paper.
4.3.3 The Supplemental
A. Budgets and Schedules
I. Cost Budget
The budgets should be presented in the form of the sponsor request. It should on more than
one to two pages. But if should contain all the costs needed.
Most proposals put together with the expectation that funding will be necessary and an
itemized list of the items needed to carry out the research is listed in some detail. A carefully
developed budget reflects the seriousness of the proposal and the degree to which it is a
realistic assessment of what is needed. A detailed, carefully through out budget will, be
48
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
useful in planning, implementing and monitoring the project. The following points should
come in mind when preparing the budget.
 It may be convenient to use the work plan as a starting point
 Specify for each activity in the work plan what resources are required.
 Determine for each resource the unit cost and the total cost.
 Keep some amount of contingency-5%
II. Budget of Time (Schedule)
A time table explaining how the research expects to carry out his project and when each of
the important phases will be completed is help full to both the researcher and the reviewer. It
is even important that the disbursement of the research fund is based on the time schedule for
most of the research under takings.
A work plan is a Schedule, chart or graph that summarizes in a clear fashion, various
components of a research undertaking and how they fit together. The plan includes the
following components like:
-task to be performed
-when the tasks will be performed
-who will perform the tasks.
Your schedule also include the major phases of the project (study), their time tables, and
milestones that signify completion of a phase. For example, major phases may be
(1) exploratory interviews,
(2) final research proposal
(3) questionnaire revision,
(4) field interviews,
(5) editing and coding,
(6) data analysis, and
(7) report generation. Each of these should have on estimated time schedule.
B. Reference Section
All works cited in the proposal are listed here. The sources are many, i.e., text books,
Journal, articles, etc…., Published and/or unpublished, could be possible to cite, quote, or
paraphrase as to their relevance to your study
49
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
 Unpublished Works are
-Personal communication with experts, professionals,
-Unpublished data
-Unpublished research works
-Organization’s reports
-Public speeches
-Conferences
The researcher should not put such unpublished work in reference list. Such reference should
be placed in the body of the text.
Example
“ ………………………………………..” (MTI’s annual report)
C. Appendices
Materials which may help the reader to get some more knowledge about the study you
conducted.
It is not mandatory to have this section. If the researcher thinks that having this section will
increase the quality of the proposal, he is free to do so. Information types provided in this
section are those additional details, which are difficult to accommodate with in the standard
headings. Staffs to be included in the appendix are: details questionnaires are interview
schedule survey and other geographic maps, photographs and statistical procedures and
formulas.
50
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
CHAPTER FIVE
RESEARCH METHODOLOGY
Research methodology constitutes two major elements. These are (1) the sampling
procedures, (2) the source and collection of data. The methodologies are the core and the
largest part of a scientific research proposal which are largely descriptive in nature. This
section is an essential prerequisite for validating the results and hence acceptability of the
proposal. Methodologies should give full details to show how the research activity is going to
be carried out. Since this section is the largest and the most important of the research
proposal, researchers are advised to split it in to sub-sections. Such effort makes the proposal
transparent and clear to the readers as well as to the sponsor and therefore, minimizes the
risks of being rejected.
5.1 Sampling Design
The basic idea of sampling is that by selecting part of the elements in a population,
conclusion may be drawn about the entire population. An element is the subject in which
measurement is being taken. It is the unit of the study. A population is total collection of
elements about which we wish to make some information. A census is a study including all
the elements in the population.
It is needless to say that no investigator can study the entire population and hence selects a
few individuals belonging to a population for the purpose of his investigation. These selected
individuals form a sample and while selecting these individuals the investigation should
consider the following facts.
5.1.1
Definition of Population
The investigator should define population in operational terms, describing it with all the
necessary identifiable characteristics. This helps the investigator in selecting the sample
depicting the same characteristics with more case and further helps the investigator in
generalizing his findings of the present investigation with more authenticity. Thus the only
difference between the population and the sample is their size and except for that, the sample
is exactly similar to the population in all characteristics.
51
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
5.1.2 Sample Size
Depending on the mode of research the sample size varies. For example, in experimental
research the sample size is very small compared to that of descriptive research. It is always
advisable to collect data from more number of individuals than required by sample size, to
take care of any causality, particularly in the case of problems where the data is to be
collected from the same sample repeatedly at different times. Sample size is usually
determined by estimating the reliability of statistics calculated from the data collected from
different sizes of the samples.
A. Representativeness of the Sample
When a sample is selected, it is assumed that it represents the population for which it stands.
Failure of this is failure of entire research study. This is fundamental and critical in any
research design to give sense to any research study undertaken. Thus the investigator should
use his ingenuity in carefully selecting the appropriate technique of sample selection.
The different techniques usually complied by the investigators in selecting the sample varies
accordingly- the one selected depends on the requirements of the project, its objectives, and
funds available.
Further more, the members of a sample are selected either on a probability or non-probability
basis. Probability sampling is based on the concept of random- selection- a controlled
procedure that assures that each population element is given a known non zero chance of
selection. Non- probability sampling, on the other hand, is subjective and each member does
not have a known non zero chance of being included.
The major concern in sampling is a choice of sample that is representative of population. A
sampling is representative if it generates a result that would be reached it the research were
conducted on the whole population. In order to be representative, a sample should possess all
the important characteristics of the population from which it is drawn.
B. Factors that Determine the Size of the Sample
I. Nature of the Study
Nature of the study affects the size of a sample for intensive and continuous study small
sample will be suitable, because such study in a large sized sample will require more
52
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
resources. For general survey, the size of the sample should be large, but for technical studies
the size of the sample should be kept small
II. Type of Sampling
In random sampling, greater accuracy in results will be achieved only in a large sample. In a
properly drown stratified sampling, a small sample can give more accurate results.
III. Nature of Units
Where it is expected that a large number of unit will not respond, then a large sample should
be taken.
IV. Size of Questionnaire
If the size of the questionnaire is large and it contains difficult questions, the size of the
sample should be kept smile.
V. Practical Considerations
The availability of finance, time and trained personnel are other practical considerations,
which affect the sample.
5.1.3 Methods of Sampling
A. Probability Sampling
In this type of sampling each member of a population has a predetermined chance
(probability) of being induced in a sample. There are different methods of selecting a
probability sample let’s see them one- by – one.
I. Simple Random Sampling
A simple random sampling is one in which each item in the universe has an equal or known
opportunity of being selected. It is more suitable in more homogeneous and comparatively
large groups. Three methods are generally used for drawing out a sample on simple random
basis.
a. Lottery Method
A simple method to do this is to list numbers and to drew lotteries or to use dies or charts or
systems prepared for this purpose.
b. Use of Tables of Random Numbers
These numbers are very widely used in all the sampling techniques and have proved to be
quite reliable as regards accuracy and representative ness.
53
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
c. Precautions in Drawing a Simple Random Technique
Population to be sampled and the unit must be clearly defined.
Different units should be approximately of equal size.
The unit must be independent of each other
Method of selection should be completely independent
Every member should be accessible units once selected should not be ignored or replaced
by any other unit of the universe
d. Merits of the simple Random Technique
It eliminates bias and is more scientific method of taking samples
Assessment of the accuracy of the result is possible by sample error estimation
The sample drawn under this method is true representative of the universe
It is very simple and easily practicable of selecting samples.
e. Demerits of the simple Random Technique
It requires complete list of the universe that restrict the use of this method
It is not suitable for respondents (dispersed) over a large geographic area.
For a given degree of accuracy, this method usually requires large samples as compared
to stratified sampling.
II. Complex Random Sampling
Simple random sampling is often impractical. It requires a population list that is often not
available. The design may also be wasteful because it fails to use all the information about a
population. In addition, the carrying out of a simple random design may be expensive in time
and money. These problems have led to the development of alternative designs that are
superior to the simple random design in statistical and /or economical efficiency. In the
discussion that follows, four alternate probability sampling approaches are discussed;
systematic, stratified, cluster and double sampling methods.
a.
Systematic Random sampling
Under this method a sampling is taken from a list prepared on a systematic arrangement
either on the basis of alphabetic order or on house number on the basis of alphabetic order or
on house number or any other method. In this method only the first sample unit is selected at
random and the remaining units are automatically selected in a definite sequence at equal
spacing from one another.
54
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)

Steps Involved in systematic random sampling
-Arrange population in serial numbers from 1 to N and determine the size of the sample,
-Determine the sample interval by dividing the population by sample size as follows.
N/n=K
Where, K= Sample interval
N= Sample size
N= Population size
-Select any number at random from the first sampling interval. The subsequent samples are
selected at equal or regular intervals
ii. Merits of systematic random sampling
-It is easy to operate and checking can also be done quickly
-It results in representative sample because of its randomness and
probability features.
iii. Demerits of systematic Random sampling
-It works well only if the complete and up- to – date frame is
available and if the units are randomly arranged.
-Any hidden periodicity in the list will adversely affect the
representativeness of the sample.
b. Stratified Sampling Method
When the population is heterogeneous with respect to the variable or characteristics under
study, then the techniques of stratified sampling is used to obtain more efficient and accurate
results. Stratification means division of the universe into groups according to geographical,
sociological or economic characteristics.
i. Processes Involved in Stratified Sampling
-Divide the universe in to sub-groups. Then the required units are selected at random from
each sab-group.
-Conduct the stratification in such a way that item in one stratum should be similar to each
other but different significantly from unit of other strata
-Each and every unit in the population must belong to one and only one stratum, i.e., various
strata must be non-over lapping
55
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
-The size of each stratum in the universe must be large enough to provide selection of item in
random basis.
-Size of the sample from each stratum can be proportional or disproportional to the size of
each stratum.
ii.
Merits of Stratified Sampling
-If a correct stratification has been made even a small number of units will form a
representative sample.
-Under this method, no group is left unrepresented
-It is more precise and avoids bias to a great extent.
-It is the only sampling plan, which enables us to achieve different degrees of accuracy for
different segment of the population.
-Replacement of case is early in this method if the original case is not accessible to study
-It enables different research methods and procedures to be used in different strata
-Stratification is usually more efficient statistically than simple random sampling and at
worst is equal to it. With the ideal stratification, each stratum is homogeneous internally and
heterogeneous with other strata.
iii. Demerits of Stratified Sampling
-It is a very difficult task to divide the universe in to homogeneous strata the universe in to
homogeneous strata
-If the strata are over-lapping, unsuitable or disproportionate, the selection of samples may
not be representative
-Disproportionate stratification requires weighting which again introduces selective factor in
the sample and under weighting makes the sample unrepresentative.
c. Cluster sampling
In a simple random sampling, each population element is selected individually. The
population can also be divided into groups of elements with some group randomly selected
for study.
This is cluster sampling. An immediate question might be how does this differ from stratified
sampling? They may be compared as follows.
56
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)

In stratified sampling, we divide the population into a few sub- groups, each with
many elements according to some criterion that is related to the variable under
study; while in cluster sampling, we divide the population in to many sub- groups,
each with a few elements in it. The sub groups in the later are selected according
to some criterion of ease or availability in data collection.

In the former one, we try to secure homogeneity with in sub-groups and
heterogeneity between subgroups; while in the later one, we try to secure
heterogeneity with in sub group and homogeneity between sub- groups, but we
usually get the reverse.

In the former one, we randomly choose elements from with in each group; while
in the later one, we randomly choose a number of the sub-groups, which we then
typically study in to.
When properly done, cluster sampling also provides an unbiased estimate of population
parameters. Two conditions foster the use of cluster sampling are (1) the need for more
economic efficiency than can provided by simple random sampling and (2) the frequent un
availability of practical sampling from for individual elements.
i. Principles of cluster sampling
-Cluster should be as small as possible with the cost and limitation of the survey
-The number of sampling units in the cluster should be approximately the same
ii. Merits of cluster sampling
-It gives significant cost gain
-It is easier and more practical method, which facilitates the field work
iii. Demerits of cluster method
-Probability and the representativeness of the sample are sometimes affected if the number of
the clusters is very large
-The results obtained under this method are likely to be less accurate if the number of
sampling units in each clusters not approximately the same.
B. Non-probability Sampling
Probability sampling procedures that include some form of random selection are not always
appropriate or desirable. There are a number of reasons why simple random sampling may
57
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
not be appropriate. For example, a researcher may not have access to the whole group. Also
it may be economically difficult and time consuming to take samples from the possible study
population. In non- probability sampling method there is no assurance that every member has
some chance of being included in a sample. This can be employed in different ways.
Non-probability sampling, also called judgmental sampling method is based on the personal
judgment. Under this method a desired number of sample units are selected deliberately or
purposely depending up on the object of the inquiry so that only the important items
representing the true characteristics of the population are included in the sample. Under such
conditions, there is greater opportunity for bias to enter the sample selection procedure and to
distort the findings of the study. If this is so, why would anyone choose it?
There are some practical reasons for using these less precise methods. These are:
It is appropriate for exploratory types of researches where one may wish to contact only
certain persons or cases that are clearly non-typical. This is the case when there is no
desire to generalize about population.
It saves time and money probability sampling clearly calls for more planning and
repeated call backs to assure that each selected member is contacted.
While probability sampling may be superior in theory, there are break downs in its
application.
Sometimes non-probability sampling may be the only feasible alternative.
I. Types of Non-Probability Sampling
a. Convenience Sampling
Non-probability samples that are unrestricted are called convenience samples. They are the
least reliable design but normally the cheapest and easiest to conduct. Researchers or field
workers have the freedom to choose whomever they find, thus the name convenience.
Examples include responding to question of the researcher.
While a convenience sample has no controls to ensure precision, it may still be a useful
procedure. In the early stages of exploratory research when you are seeking guidance, you
might use this approach.
58
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
b. Purposive Sampling
A non-probability sample that conforms to certain criteria is called purposive sampling.
There are two major types- judgment sampling and quota sampling.
i. Judgment sampling
Judgment sampling occurs when a researcher selects sample members to conform to some
criterion. In a study lab our problem, for example, you may want to talk only with those who
experienced on-the-job discrimination.
When used in early stages of an exploratory study, a judgment sample is appropriate.
When one wishes to select a biased group for screening purposes, this sampling method is
also a good choice.
ii. Quota Sampling
Quota Sampling is the second type of purposive sampling. We use it to improve
representativeness. The logic behind quota sampling is that certain relevant characteristics
describe the dimension of populations.
In most quota samples, researchers specify more than one control dimension each should
meet two tests
(1) it should have a distribution in the population that we can estimate, and
(2) it should be pertinent to the topic studied.
We may relieve that responses to a question should vary, depending up on the gender of
respondents. If so, we should seek proportional responses from both men and women. We
may also feel that diploma and TVET students differ from degree students, so this would be a
dimension.
Quota sampling is a special type of stratified sampling. Here, the population is first stratified
on some basis, preferably on the basis of the characteristics of the population under study.
After this the number of sample units be selected from stratum is decided by the researcher in
advance. This number is known as quota which may be fixed according to some specific
characteristics such as in come groups, sex, occupation, political/ religious affiliations, etc.
The choice of the particular units for investigating is left to the investigators themselves. The
investigators try to get required in formation quickly by applying their judgment in the choice
of the sample
59
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
In case of non-response due to uncooperative nature of respondents, the investigator select
some fresh units himself to complete his quota.
a. Merits of Quota sampling Method
-Because it is both stratified (probability) and purposive (non-probability), it enjoys the
benefits of both methods and hence is both practical and convenient.
-If proper controls or checks are imposed on the investigator, quota sampling is likely to give
accurate results.
b. Demerits of Quota sampling Method
-It suffers from the limitations both stratified and purposive sampling
-Control over field work is difficult task. Hence the results may be biased because of the
personal beliefs and prejudice of the investigator in selection of the unit under study.
-Since quota sampling is not based on random sampling, the sampling error can’t be
estimated.
-The bias may also occur due to substitution of unlike sample units.
In general purposive sampling (embraces judgment and quota sampling) is the situation
where the researcher deliberately selects certain units for study from the universe and nothing
is left to chance.
5.2 Data Collection
5.2.1 Construction/Adaptation of Instruments
The investigator should now find instruments for collecting the data required by the
hypothesis. The investigator himself may have to construct these instruments or he may have
to adopt the readily available instruments to suit the local conditions. In the later case, the
investigator may make certain necessary changes in the format, etc., with the help of the feed
back received by conducting a pilot study on a very small sample.
Besides using the instruments, like questionnaires, interview schedules, projector techniques,
attitude scales, etc…, the investigator may adopt other methods like observation, examination
of records and so forth for data collection each of these various methods has its own
advantages and limitations, which will be discuss in details forward.
60
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
5.2.2 The Source of Data
We classify information sauces in to primary and secondary types.
A. Primary Data
Primary data come form the original sources and are collected especially to answer our
research questions. Primary data are Original observations collected by the researcher or his
agents for the first time for any investigation and used by them in the statistical analysis.
B. Secondary Data
Secondary data Studies made by other for their own purposes represent secondary data. The
different between primary and secondary data is only the degree of detachment with the
original source. Once the primary data have been used, it loses its original character and
becomes secondary. Such secondary data are mostly published in news papers, periodicals
and Journals.
C. Choices between Primary and Secondary Data
The Choice between primary and secondary data mainly depends up on the nature, objectives
and scope of inquiry, availability of time and money, degree of accuracy desired and the
status of the investigator.
The primary data are more reliable on the face, but the secondary data can be relied only be
examining the source from which they have been obtained. Their true significance is
incompleteness and methods of collection. Some times in a certain investigation both
primary and secondary data are used as supplement to one another.
The following points are note worthy for the preference of primary source in comparison to
secondary sources:

The primary source gives data in greater details compared to secondary source.
The Secondary source often omits part of the information.

In the secondary source, there is a possibility of mistakes due errors in
transcription made then the figures were copied from the primary source.

The primary sources include definitions of terms and units used. It is essential
that the investigations understand the meaning of units in which data are
recorded.
61
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)

The primary source also includes a copy of the schedule used in data collection
together with the prescription of the procedure used in selecting the sample and
the size of a sample.

The availability of time at the disposal of investigations also affects the choice
of the method to be adopted in the collection of data. If the data are needed
immediately, we have to depend on the secondary source. On the other hand, if
the time is sufficient it is recommended to use primary method of data are
more accurate and reliable compared to secondary data

The availability of finance also influences the method to be adopted in the
collection of data. If the data collecting authority has vast financial resources at
its disposal it is better to adopt primary method. On the contrary, it the data
collecting agency has less financial resources, secondary source should be
adapted even though the secondary data are not as reliable as primary data.

The availability of trained investigators also affects the choice of the method to
be employed in data collection. If trained investigators are availability, primary
method should be adapted for the collection of data. In case of non-availability
of trained investigators, it is recommended to adopt secondary method of data
collection.

The objective and the scope of the inquiry also determine the method to be
adapted in the collection of data. The selected method must suit the objective
and the scope of the inquire.
D. Qualitative vs. Quantitative Data
It is common for researcher to make a clear distinction between quantitative researches (also
known as positivistic) that focuses on scientific sampling and the analysis of numerical data,
and qualitative research (also known as interpretative) that focuses on less rigorous (or
convenience based) sampling and gathering textual information for non-statistics analysis.
Often, however, more mixed approaches (pluralistic) are used in which both quantitative and
qualitative approaches are blended and used to inform the findings of each other.
There are vast differences between the first two methods, and it is necessary to understand
their special characteristics in order to make the right selection.
62
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
 Quantitative Research is

The traditional mainstay of the research industry and it is sometimes
referred to as ”survey Research”

Quantitative research is defined as research involving the use of
structured questions where the response options have been
predetermined and a large number of respondents are involved.

Quantitative research often involves a sizable representative sample
of the population and a formalized procedure for gathering data.

The purpose of quantitative research is very specific, and this
research is used when the manager and researcher have agreed that
precise information is needed.

Data format and source are clear and well defined, and the
compilation and formatting of the data gathered follows an orderly
procedure that is largely numerical in nature.
 Qualitative Research, in contrast

Involves collecting, analyzing, and interpreting data by observing
what people do and say.

Observation and statements are in a qualitative or non- standardized
form.

Because of this, qualitative data can be quantified but only after a
translation process has taken place. For example, if you asked five
people to express their opinions on promoting alcoholic beverages to
college students, you would problem get five different statements,
but after studying each response, you could characterize each one as
“positive”,” negative”, or” neutral”. This translation step would not
be necessary if you instructed them to predetermined response
options such as “yes” or “no”.

Any study that can be ducted using an observational technique or
unstructured questioning can be classified as qualitative research.
63
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
 Pluralistic Research
Although there are proponents of both types of research, many social researchers have been
adopting pluralistic research.

It is defined as the combination of qualitative and quantitative
research methods in order to gain the advantage of both

With pluralistic research, it is common to begin with exploratory
qualitative techniques as for example, in–depth interviews of
selected dealers or a series of group discussion with customers in
order to understand how they perceive a certain product and /or
service as compared to those of competitors.

The qualitative phase serves as a foundation for the quantitative
phase of the research project because it provided the research
problem. Armed with this knowledge, the researcher’s design and
execution of the quantitative phase is invariably superior to what it
might have been without the qualitative phase.

With pluralistic research, the qualitative phase serves to frame the
subsequent quantitative phase.

Qualitative input is especially useful in helping to select areas for
surveying. The input gained through semi-structured interviews or
focus groups conducted with key participants in the social
relationship often helps to surface important new areas that warrant
inclusion and investigation.

And in some case, a qualitative phase is applied after a quantitative
study to help the researcher understand the findings in the
quantitative phase.
N.B. Source of secondary data includes official publications of central government,
publications of semi-government statistical organizations, publications of research
institutions, publications of commercial and financial institutions, Reports of various
committees and commissions appointed by government, news papers and periodicals,
internationals publications, etc.
64
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
5.3 Types of Data Collecting Tools
5.3.1 Questionnaires
The collection of data through questionnaire is one of the most popular methods used these
days. A questionnaire contains many questions pertaining to the field of inquiry and provides
space for answers.
It may be defined as an instrument for collecting information from a number of persons,
supposed to posses it by making them record their replies to a number of questions. It may be
sent to the informants by mails or delivered at hand. The informant’s sends back the
questionnaire duly filled in with in the stipulated time mentioned in the questionnaire’s
preface or introductory lines.
A questionnaire is an instrument consisting of a series of questions about the topic of the
research. It is a highly structured method of data collecting tool. It is a format containing a
list of questions sequentially ordered to obtain information relevant to the objective of the
study.
Questionnaires can be classified in terms of the nature of questions that are used: You might
have employed true/ false, multiple choice, matching, short answer questions. In this case,
“X” or “V” on some alternatives provides provided or by writing responses in words. Here
while the question that require you to put a mark are called close-ended questions; those
which require you to write your responses, in words, are known as open-ended questions.
A. Close Ended Questionnaire
These are also called restricted or structured type. Here respondents are given a set of
alternatives from which they are asked to choose the one that most closely represents their
view. They are categorical questions, which offer a list of options or answers from which the
respondent selects the one fits his/her situation. They are objective type in their nature.
Can you mention some advantages of presenting close- ended questions?

They are easy to responds,

Face little time to fill out,

Easy to tabulate and analyze etc.

An extensive field may be surveyed and information elicited from
persons living over a wide geographical area.
65
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)

Very economical both in time and money because it is usually a one
– person job.
Can you mention the major limitations related to close-ended questions?

Sometimes the choices given may not be exhaustive
The researcher should strive to include all possible choices. However, sometimes, the list of
possible choices could be very long. Under such Circumstance, only the major options
should be included by making intelligence questions. For minor ones, put the option “others”
with blank space to be filled on

Some questions are not mutually excusive
To be effective, but the items in the choice should be matually exclusive and should not over
lapping.

Some questions that are asked might be defective that demand other questions to
be answered before them.

Preparing close –ended questions is time consuming
More over, all thought questions are good and convenient for busy respondents and
enhances or simplifies tabulating, they deprive opportunity to comment on issues by
some of the curious respondents, preparing such questions presupposes deep knowledge
of the problem understudy and possible responses to the questions.
B. Open-ended Questionnaires
A questionnaire consisting of questions that are not followed by and kind of specified
choice but requires respondents to write their answer is referred to as open-ended
question.
Direct questions dealing with motives rarely elicit useful answers. Instead of approaching
the respondents with a fixed list of questions, the researcher attempts to get respondents
to talk freely about the subject of interest. By doing so, the researcher hopes to put
respondents at ease and to in coverage them to express any ideas which they have on the
subject.
Open- ended questions invite free responses. Here the respondent is not provided with a
list of answers and is given n opportunity is not provided with a list of answers and is
given an opportunity to give responses that go beyond statistical data and/or factual
information.
66
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
It enables to get opinions, attitudes, presupposes, decisions and so on.
They provide the opportunity for an in depth and detail treatment of questions for the
respondents none the less, because it takes much of the respondents time and requires
deep knowledge, many of such questions practically may not given answers. The task of
tabulating and summarizing such questions would also be firesome.
 How do you make preference between close – ended and open- ended questions?
The preference between close-ended and open-ended questions depends on the following
points.

The aim of the researcher
If the objective is to categorize subjects, close ended questions are appropriate. If detailed
information is needed on the issues, open-ended questions are preferred

The subject level of knowledge on particular issue
If the subject has through knowledge on the issue, open-ended questions are preferred and
vice versa

The extent of structure that features subject opinion on the issue
If the respondents, views on the particular issue, are properly formulated, we should opt for
closed-end questions. Other wise, open – ended questions are preferred.
 The convenience with which the material can be communicated
If there are no outstanding obstacles to communicate, close ended questions would be
appropriate.

The researcher’s information and insight into the subjects` condition
If the researcher is knowledgeable about the subject, the best option would be to make close
ended questions and vice versa.
Mean while, the types of questions can not mutually exclusive, i.e, we can use
both of them at the same time. However, it is preferable to use many closeended questions and to include few open ended questions.
C. Developing a Good Questionnaire
A good questionnaire is one that helps the researcher to obtain data related to the objectives
of the study. The topic areas to be covered or the content of the questionnaire value out of
what the researcher wants to accomplish from the proposed project. The types of questions or
67
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
items to be included in the questionnaire and the questionnaire and the format depend to a
large extent on the types of data sought and the questionnaire design concepts and alterative.
The researcher can not develop a good questionnaire simply by increasing down what he
thinks will provide him the type of data for which he is looking. Various steps are involved in
developing a questionnaire that will provide the researcher with needed data. These steps are.
i. Determining Questionnaire Contents
In determining the contents of the questionnaire, the researcher should consider the problem
he wants to investigate the objectives or the hypothesis to be tasted. Once these are specific
and clear, the researcher should determine the contents of the questionnaire.
ii. Developing Items to be Used
Once the researcher decides up on the content areas for the questionnaire, the next step in to
develop items with which to obtain data related to the content areas. The items can be
questions or statements. They can be in the form of (a) structured or non-structured question,
(b) rank-ordered questions, (C) rating Scales, and (d) attitude scales, seldom are all these
types put in any one questionnaire It is common, how ever, to have a combination of one or
more types in a single questionnaire.
iii.
Preparing the First Draft
Based on decisions made on item to be included in the questionnaire, the researchers do not
develop the initial draft. This phase used a trial and error approach with regard to the
sequencing or arranging of items or questions and reviewing and revising until the researcher
feels that the items are appropriate.
Sequencing items in a proper order is necessary because the questions included in the
questionnaire, should be organized into logical groups. Grouping can be made on the basis of
questionnaire content or on type of format of the items. Each section in every items or
question must be reviewed to determine the type of instruction that should be given to the
informants to facilitate each and accurate completion of the questionnaire.
iv. Pre – Testing
The revised draft should be tested before data are collected. The revised questionnaire should
be pre-tested to determine how well it serves the purpose of obtaining needed data. Pretesting
68
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
to be done by administrating the questionnaire to small but representative sample of potential
respondents under conditions that are identical in all respects to those under which final
questionnaire will be administered.
V. Revising and writing the final Questionnaire
How much and to what extent a questionnaire subjected to pre test should be revised is
primarily at the researcher’s discretion or judgment. If a substantial number of respondents in
the sample find it difficult to understand an item, it should be revised.
Organization of the testing procedure and control are essential to reap the full benefits of pertesting and arrive at a questionnaire which will accomplish the objectives of the study. After
the test questionnaire is revised, the researcher should prepare the final questionnaire. In
preparing the final questionnaire, the researcher must take in to account every aspect of the
criticism of the initial draft and the results of pre-testing.
5.3.2 Interviews
Interviews are the process of interaction or communication in which a sample subject gives
the needed information verbally in a face to face situation. Interviewer involves interaction so
that there will be at least two individuals- the interviewer and interviewee.
Interview is to be conducted verbally, the interviewer and the interviewee being in a face to
face situation, it is intended to get information.
There are various types of interviews, and person administered interviews such as, (1) the inhome interview, the mall intercept interview, the in-office interview, and the telephone
interview, and their variations are largely based on the location of the interview.
Using interview will enable a researcher to get in –depth information by clarifying questions
he asks more and more to interviewee.
Hence, a personal interview is a two-way conversation initiated by an interviewer to obtain
information from respondents; the consequences of the event are usually insignificant for the
respondent the respondent is asked to provide information with little hope of receiving any
immediate or direct benefit from this cooperation.
Yet if the interview is carried off
successfully, it is an excellent data collection technique.
69
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
Using direct personal interviews data are collected by the investigator personally by asking
questions pertaining to the enquiry from persons from whom the information is to be
obtained. Thus, if a person wants to study the spending habit of the students of a university
he may contact and interview students personally and collect the desired information. If an
enquiry is to be conducted in to the family budgets and living conditions of workers of
factory, the investigator may interview the workers and collect the information necessary for
his investigation.
A. Merits
Following are the advantages of direct personal interview method:

As the investigator approaches the informants personally, it enable to
secure depth and detail, information.

The results obtained by this method are generally accurate and
reliable as the enquiry is intensive and is conducted personally. The
investigator can remove the doubts of the informant about certain
questions. Also if the investigator has any doubt about the answer to
a question he can get it removed from the informants by asking the
question again.

The interviewer establishes personal contact and can twist the
questions keeping in mind the informant’s reaction.

The language of communication can be adopted according to
educational level of the informant.

Any other additional information about the personal characteristics
of the informants may be collected, which will provide a background
at the time of interpretation of data

Interviews can use special scoring devices and visual materials.
70
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
B. Limitations
Some limitations of this method are:

Its nature limits its scope. It can not be extensive in its scope. If the
number of persons to be interviewed is large and they are spread
over a wide area, these methods can not be useful as it requires the
personal attention of the investigator.

If the inquiry is a bigger one, then it can not be completed with in a
reasonable time. Thus it is costly in terms of many and time.

The subjective factor is generally involved either consciously or
unconsciously.

The interviewers have to be thoroughly trained and supervised, other
wise results obtained may not be accurate and reliable.
C. Structured and Unstructured Interview
Like the questionnaire method, interview method also classified in to structured and
unstructured interview methods.
In structured interview method, the researcher makes some procedures before conducting the
interview. The same type of questions is presented in the same order to each subject. The
interviewer has no freedom to rephrase or modify the questions, to add extra ones or to
change their order.
? What benefit do you think a structured interview will have to a researcher?
Presenting similar questions to all subjects in the same sequence will enable the researcher to
compare their responses. So that variations in responses will be attributed not due to
variations in the interview but due to actual differences between the respondents (Subject).
Structured interview may also present to the interview questions that do have alternative
responses. For example, in a study to discover the types of conflict between parents and
teenagers, a researcher may raise the following question to the interviewee.
Have you ever had any disagreement with either of your parents (father or Mother) because
of
a, drinking?
b, too many friends ?
71
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
c, dating with opposite sex?
d, smoking ?
Then following this question other subsequent questions may follow to get more elaboration
of the response.
On the other hand, unstructured interview, like open-ended questionnaire, provides greater
flexibility- Although the series of questions to be asked and the procedure to be followed are
decided before hand; the interviewer is largely free to arrange the form and filming of the
questions. He can thus rephrase the questions, modify them, and add some new questions to
his list while conducting the interview.
Advantage of using unstructured interview is similar to that of open- ended questionnaire it
allows the respondent to express his\her view in the way he\she likes. It permits much
freedom to the interviewees to talk about the problem under investigation. And as a result we
will be able to get in depth information. But unstructured interview is not with out
limitations. The researcher may face problems of organizing, categorizing and analyzing
information obtained through unstructured interview.
5.3.3. Observation Method
Observation is the technique which involves systematic collection, watching, and recording
of behavior and characteristics of living beings, objects or other phenomena. In our every day
life we are all observers. We constantly observe the physical environment and the people
around it. Observation involves watching but information from sight is supported by that
received through other senses: through hearing, smelling, touching, and tasting. The
information from these various senses are usually combined, processed and interpreted in
complex ways to form our observations our mental images of the world and what is going on
in it.
Observation in research, similarly, fulfils more or less & similar purposes. But there are some
important differences. Also the aim of observation in research is to collect information about
the world, how ever, observation in enable the researcher to improve his participation in the
world. Its aim is the production of knowledge about specific issues, which can be used by
others in a variety of ways. Hence, in observation type of data collection, the researcher’s eye
72
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
is the most important research tool, and the method is the most straight forward approach of
studying the subject’s outward behavior.
A. The Observer- Subject Relation Ship
The relationship between observer and subject may be viewed from three perceptive: (1)
whether the observation is direct or indirect, (2) whether the observers presence is known or
unknown to the subject, and (3) what role the observer plays.
I. Directness of Observation
Direct observation describes the situation in which the observer is physically present and
personally monitors what takes place. This approach is very flexible because it allows the
observer to react to and report subtle aspect or events and behaviors as they occur
A weakness of this approach is that observers perception circuts may become overloaded as
event move quietly. Also, observe fatigue, boredom, and distracting events can reduce the
accuracy and completeness of such observation.
Indirect observation is the study in which the recording is done by mechanical, photographic,
or electronic means. Such methods are less flexible than direct observation, but they are
much les biasing and may be less erratic in accuracy. The permanent record can also be
reanalyzed to include many different aspects of the event. It is also less costly in time and
money.
II.
Concealment
A second factor affecting the observer –subject relationship concerns whether the presence of
the observer should be known to the subject, when the observer is known, there is a risk of a
typical activity by the subjects. The potential bias from subject awareness of observers
should, therefore, be a matter of concern. Observers use concealment to should themselves
from the object of their observation. Often technical means are used such as one-way mirror,
hidden cameras, or microphones. These methods reduce the risk of observer bias but bring up
a question of ethics. Hidden observation is a form of spying, and the property of this action
must be reviewed carefully. A modified approach is partial concealment. The presence of the
observer is not concealed, but the objective and subject of interest are.
III.
Participation
Participation is the third observer – subject issue refers whether the observer should
participate in the situation while observing. A more involved arrangement, Participant
73
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
observation, exists when the observer enter the setting and acts both as an observer and a
participant. Sometimes he is known as an observer to some or all of the participants, while at
other times the true role is concealed. While reducing the potential for bias, this again rises
an ethical I Often subjects will not have given their consent and will not have knowledge of
or access to the findings. After being deceived and having their privacy invaded, what further
damage could come to the subjects if the results become public? This needs to be addressed
when concealment and covert participation are used.
Participant observation makes a dual demand on the observer. Recording can interfere with
participation, and participation can in interfere with observation. The observer’s role may
influence the way others act. Because of these problems, participant observation is less used
in social/business research than, say, in anthropology or sociology.
B. Advantages of Observational methods
There are many positive aspects of the observational research approach.

Observations are usually flexible and do not necessarily need to be structured
around a hypothesis (remember a hypothesis is a statement about what you expect
to observe). For instance, before undertaking more structured research a
researcher may conduct observations in order to form a research question. This is
what we call exploratory research.

Observational research findings are considered strong in validity because the
researcher is able to collect a depth of information about a particular behavior

It permits collection of data on facts that can’t be collected using questionnaire
and/ or interview.

The behavior of the observer can influence the situation of the observation leading
the subject to pretend and might not enable to see the reality.
C. Disadvantages of Observational Method
However, there are negative aspects.
There are problems with reliability and generalizability.
Reliability refers to the extent that observations can be replicated seeing behaviors occur
over and over again may be a time consuming task.
74
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
Generalizability (external validity) is described as the extent that the study findings would
also be true for other people, in other places, and at other times. In observational research,
finding may only reflect a unique population and therefore, can not be generalized to others.
 With direct observation, typically, only small numbers of subjects are studied and usually
under special circumstance, so their representativeness is a concern.
 The major of all observational methods is the researcher’s inability to see beneath the
behavior observed and to interrogate the person on motives, attitudes, and all of the other
unseen aspects of why, what was observed took place.
 There are also problems with researcher bias/subjective interpretation/ .Often it is
assumed that the researcher may “see what they want to see”. Bias, however, can often be
overcome with training or electronically recording observations. Hence, overall,
observations are a valuable tool for researcher.
In sum, all the instruments have got their strength and limitations. Thus whether we use
questionnaire, interview or observation, we have to establish the validity and reliability of the
instrument as well as practicality. Hence, practicality has been defined as economy,
convenience, and interpretability exactly.
75
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
CHAPTER SIX
ANALYSIS AND INTERPRETATION OF DATA
Processing of data requires editing, coding, classification and tabulation. And these are
crucial stages in a scientific research. Data collected during the research is processed with a
view to reducing them to manageable proportions. A careful and systematic processing will
highlight the important characteristics of the data, facilitates comparisons and render it
suitable for further statistical analysis and interpretations. A brief discussion of some broad
areas of work for statistical processing is given below.
6.1 Editing the Primary Data
After the data have been collected by the primary method, the next step is to edit the filled
schedules. The editing of schedules is compared to the editing of a manuscript before
publication; therefore, it has become an established practice to avail the services of trained
editors who check the schedules for accuracy as well as for consistency.
Editing is always done in the office, far away from the place of data collection. In many
cases it is not possible to check all schedules. In such cases, a sample of required size is
sufficient to ascertain the degree of accuracy of filled schedules. The duty of editing the
schedules must be entrusted to honest, efficient and sincere editors who are committed to the
job. Negligence on the part of an editor may do a lot of harm to the findings of the study.
Therefore, an editor should be a person of unquestionable integrity. The editors are required
to check the filled schedules in the following respects:
6.1.1
Editing for Consistency
The schedules are to be edited for consistency. They should see whether answers to questions
supplied by informants are consistent or not. If the answers are of contradictory nature then
the editors are required to send such schedules to respective supervisors for recording the
correct answers from concerned informants. For illustration, an informant might enter as
‘unmarried’ in one column, while the second column he may enter ‘two children’. Such
contradictory replies are to be corrected. Some is the case with age and date of birth
information, which may not agree.
76
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
6.1.2 Editing for Completeness
It is the duty of the editor to examine whether all questions in the schedule or questionnaire
are answered or not. In many cases, important questions are not answered and the analysis of
the problem is not possible due to such unanswered questions. The editor should send such
schedules to concerned investigators for recording the answers from informants.
6.1.3 Editing for Accuracy
The Job of the editor is highly specialized; therefore, he must know the nature of information
which is to be supplied by the informants. The accuracy and the reliability of the findings
depend up on accurate information, therefore, the editor has to examine whether all questions
are answered correctly or not. In case, any doubt develops about any question in the mind of
the editor, he must seek clarification from the supervisor or from the informants.
6.1.4 Editing for Uniformity
The problem under study can be rationally analyzed when there is a uniformity in the
answers of the questions supplied by different informants. Uniformity of answers mean
whether all questions are interpreted in the same sense by all informants or not. If the
questions are interpreted in different ways by different informants then the data supplied
becomes heterogeneous such data should not be employed for analysis.
6.1.5
Editors for Competitions
It is advised not to ask the investigators or the respondents supplying information to make
any computation. This additional work may give risk to errors computations, if necessary,
should always be made by editors.
6.2 Coding
After editing of the collected data, the next step to follow is coding. Coding refers to
assigning of number digits or letters or both to various responses so as to enable tabulation of
information easy. The purpose of coding is to classify the answers to a question in to
meaningful categories which is essential for tabulation.
According to M. Parton, “coding consists in assigning a number of symbols to each answer
which falls in a predetermined class.”
Goode and Halt defines coding as “An operation by which data are organized in to classes
and number of symbol is given to each item according to the class in which it falls.”
77
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
The need of coding arises more in the case of quantitative data which is a pre- requisite for
any meaningful interpretation of social data. Coding in the modern age of computers is done
after translating the information collected in the usual manner in to language of machine.
In most surveys, certainly whenever results are to be put in quantitative form, the
intermediate stage is the coding of the answers. Some times this and the initial editing are
joined in a single operation.
The purpose of coding is to classify the answers to a question in to meaning full categories,
so as to try out their essential pattern.
The process involves two distinct steps. The first is to decide on the categories to be used, the
second, to allocate individual answers to them. The set of categories to be used will be
referred to as the coding frame. The set of coding frames covering all the information to be
abstracted from the questionnaires is commonly known as the code book.
6.2.1 The Coding Frame
A coding frame relates to a single question. In cases where there are only a few possible
answers to the questions, the preparation of the frame raises on problems.
6.2.2 The Question
“Have you smoked any cigarettes today”? Admits only of the answers “yes” or “No”
together with ‘Don’t remember,’ ‘Refuse to answer’, ‘Not applicable’, so that the frame
decides itself. Where the frame does not determine it self automatically, it is a matter of
deciding how detailed a grouping to allow for in the coding, which in turn depends on how
the answers are expected to be distributed and what analysis is being planned.
6.3 Classification
Once the data is collected and edited, the first task of the statistician is the organization of the
figure in such a form that their significance, for the purpose in hand, may be appreciated that
comparison with masses of similar data may be felicitated, and that further analysis may be
possible. This is done through classification and tabulation. But be for tabulating the data in
to different homogeneous classes, it is necessary to sort out the relevant and significant
78
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
features from the irrelevant and insignificant ones. The process of arranging the data in to
groups or classes according to resemblance and similarities is technically called classification
It is of interest of give below the following definitions of classification.
Classification is the process of arranging data in to sequences and groups according to their
common characteristics, or separating them in to different but related parts. (- secrist)
A classification is a scheme for breaking a category in to a set of parts, called classes,
according to some precisely defined differing characteristics possessed by all the elements of
the category.(- Tuttle A.M)
Thus classification impress up on the ‘arrangement of the data in to different classes which
are to be determined depending up on the nature, objective and scope of the enquiry.
6.3.1 Objects of Classification
The chief objects of classification are to:

present the facts in a simple form

bring out clearly points of similarity and dissimilarity.

facilitate comparison

bring out relationship

present a mental picture

prepare the basis for tabulation
6.3.2 Characteristics of Classification

The classification system must be exhaustive

The classes must not over lap

Stability is crucial- classification must proceed at every stage in accordance with one
principle, and that principle should be maintained throughout.

A good classification should be flexible and should have the capacity of adjustment to
new situations and circumstances.

The items included in one class should be homogeneous.

The classification should conform to the object of enquiry- i.e., suitability of the
classification scheme.
79
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)

Arithmetical accuracy is mandatory- the total of the items included in different classes,
should tally with the total of the universe.
6.4 Statistical Series
A series refers to some logical arrangement of data by size, magnitudes or characteristics as
the case may be.
6.4.1
Types of Series
Following are the main types of statistical series relating to quantitative phenomena
A. Individual Series
When the measurement of individual items are arranged either in ascending order, desceding
order or according to some other scientific order, it is known as individual series.
B. Discrete Series
When we count the number of items (frequency) each value of the variable occurs, it is
known as a discrete series. The discrete series consists of two (columns) i.e., (1) the size of
measurement of variables, and (2) frequency. The frequencies are counted through the
technique of tally marks or tally bars.
C. Continuous Series
The presentation of data in to continuous series along with the corresponding frequencies is
known as continuous series. It becomes necessary in the case of some variables which can
take any fractional value and in whose case an exact measurement is not possible and when
discrete series is liked to be too long to handle.
The basic components of a continuous series are:I.
Class Interval
A large number of observations are usually classified in several groups according to the size
of value these groups are called class intervals.
II. Class Limits
Each is specified by two extreme values, called the class limits, the smaller one being called
as the lower limit and the larger one the upper limit. The class limits may be of two types,
e.g. (i) inclusive type, and (ii) exclusive type.
80
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
a. Inclusive Type of Series
In such types of series the overlapping of class intervals is avoided, both the lower and upper
class limits are included in the class intervals.
Class int. (Marks)
Number of students
0-9
10-19
20-29
30-39
40-49
50
70
120
90
70
Total
400
b. Exclusive Type of Series
Exclusive type is that a value equal to the lower limit should be included in the class interval
and a value equal to the upper limit should be excluded e.g., Mark of 400 students
Class interval (marks)
No of students
0-10
50
11-20
70
21-30
120
31-40
90
41-50
70
Total
400
6.4.2
Rules for Determining class interval
No hard and fast rules can be given but the following few facts must be taken in to account in
determining the class intervals

The range is the difference between the largest and smallest observation in the given
data. The range is divided in to a suitable number of classes by means of class intervals.

The choice of the number of class intervals basically depends upon the number of items
to be classified, the magnitude of items and the accuracy desired. It also depends up on
the case of calculation for further processing of data.
81
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)

The actual number of class intervals would also depend on the size of class intervals
because the number of classes and size of class intervals are inversely related. If one is
increased, the other is automatically squeezed. Therefore, both must be kept in mind to
form a suitable distribution.

According to F.C Hills ‘In deciding up on the size of class intervals (which is deciding
the number of classes) one fundamental consideration should be born in mind viz the
classes should be so arranged that there will be no material departure from an even
distribution of cases with in each class. This is necessary because interpreting the
frequency table and in subsequent calculations based up on it the mid-value of each class
is taken to represent the value of all cases falling with in that class.

Number of classes should be so determined that an orderly and regular sequence of
frequencies it secured.

It is better of the class interval of all the classes are equal

Classes with zero frequency should neither be added with other classes nor should they
be omitted.

A general rule for determining the classes is to have 5- to-15 classes. The choice of actual
number of classes will depend on the number of observations and the size of class
interval required.
6.5 Tabulation
After the data has been classified, the next step is to arrange them in form of table. It is an
intermediate process between the collection of data on one hand and statistical analyses on
the other. Tabulation is regarded as the last stage in processing of data and forms the gate
way for further statistical treatment.
6.5.1 Definition of Tabulation
L.R Connor has said, “Tabulation involves the orderly and systematic presentation of
numerical data in a form designed to elucidate the problem under consideration”.
According to A.M Tuttle, “A statistical table is the logical listing of related quantitative data
in vertical columns and horizontal rows of numbers with sufficient explanatory and
82
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
qualifying words, phrases and statements in the form of titles, headings and notes to make
clear the full meaning of data and their origin.”
6.5.2 Objects of Tabulation
Tabulation is a process which helps in understanding complex numerical facts.
According to D.W Paden and E.F Linduist, “The purpose of table is to summarize a mass of
numerical information and to present it in a simplest possible form consistent with the
purpose for which it is to be used. In a very real sense, the statistical table serves the
statistician in much the same fashion that poetry serves the writer -it is a medium of
communication of great economy and effectiveness for which ordinary prose is inadequate.
In addition to its function in simple presentation, the statistical table is also a useful tool of
analysis.”
Tabulation has the following objectives to fulfill to:
a. clarify the object of investigation,
b. clarify the characteristic of data,
c. present facts in the minimum of space,
d. facilitate statistical processes,
6.5.3 Advantages of Tabulation
Tabulation is an important process between collection and classification of data and their
interpretation. The tabular presentation of data has several distinct advantages. They are:A. It simplifies facts
Tabulation is helpful in presenting mass of complex data clearly, so that their features can
easily be understood.
B. Economy
It occupies less space than textual reports, hence saving of paper and time Required figures
can be located more quickly.
C. Helpful in Comparison
Tabulation makes comparison easy comparable figures are placed in Juxtaposed columns,
hence a comparative study can be made.
83
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
D. Facilitates of Computation
It helps in computation of different statistical measures. For calculating average, dispersion,
correlation, etc. data must be presented in tables
E. Helps Classification
While classification is a theoretical process of data analysis, tabulation is an applied process.
Tabulation is helpful in classification also. After classifying data the characteristics of
different classes are not clear till they are placed in a suitable table.
F.
Helps in Reference
Tabulated data are good for reference purposes.
G.
Helps in Interpretation and Presentation
It is convenient to interpret and tabulated data make it easy to present the facts in graphical
and diagrammatic form.
6.5.4 Limitations of Tabulation
Tabulation has got certain limitations as well.
A.
A table contains only figures and not their description
It is not easy to understand it by persons who are not adopt in assimilating facts from tables.
B. It requires a specialized knowledge to understand a table
A layman can not drive any conclusion from a table.
C. A table does not lay emphasis on any section of a particular importance
Therefore, the tables should be used as complementary to textual reports. Inspire of these
limitations, it is to be admitted that tabulation is essential for statistical analysis, and
hence an important part of statistical investigation.
Hence, a well- planned table is unifies, coherent and in a sense complete story about
some aspect of a set of data. A special knowledge and skill is necessary to present this
story. A good statistical table is not a more careless grouping of columns and rows of
figures; it is a triumph of ingenuity and technique, a master piece of economy of space
combined with a maximum of clearly presented information.
84
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
6.6 Analysis and Statistical Techniques
6.6.1 Meaning of Analysis
To quote prof. Wilkinson and Bhandarkar, “Analysis of data involves a number of closely
related operations that are performed with the purpose of summarizing the collected data and
organizing these in such a manner that they will yield answer to the research questions or
suggest hypothesis or questions if no such questions or hypothesis had initiated the study.”
Some scholars are of the opinion that processing of data is one under analysis of data.
Prof. John Gating had made distinction between analysis of data and the processing of data.
He is of the opinion that processing of data refers to concentrating, recasting and dealing with
the data so that they are amenable to analysis as possible, while analysis of data refers to
seeing the data in the light of hypothesis or research questions and the prevailing theories and
drawing conclusions that are as amenable to theory formation as possible.
Goods, Barr and Scates write-“Analysis is a process which enters in to research in one form
or another from the beginning…. It may be fair to say that research consists in general of two
larger steps- the gathering of data, and the analysis of these data, but no amount of analysis
can validly extract from the data factors which are not present.”
Martz has pointed out- “….bare facts, objective data, never determine anything. They
become significant only as interpreted in the light of accepted standards and assumptions,
and these standards in the final analysis are not succeptible to scientific determination. In
ordinary life we seldom deal with bare facts but facts interpreted. This interpretation or
evaluation is determined by the purpose to which we relate the facts.”
The data may be adequate, valid and reliable to any extent, it does not serve and worth while
purpose unless it is carefully edited, systematically classified and tabulated, scientifically
analyzed, intelligently interpreted and rationally coincided.
6.6.2 Data Analysis
Analysis of the data is the most skilled task of all the stages of the research. It is a task
calling for the researcher’s own judgment and skill. It should be done by researcher himself
and should not be entrusted to any other person. Proper analysis enquires a familiarity with
85
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
the background of the survey and with all its stages. The analysis does not necessarily
statistical one. Both quantitative and non-quantitative methods can be used.
The aim of analysis, eg., if it is in regard to election study is: (1) to characterize what is
typical in a votes group, (2) to indicate how widely individuals in a group vary, (3) to show
other aspects of how the individuals are distributed with respect to the variable being
measured, (4) to show the relation of the variables in data to one another, and (5) to describe
the difference between two or more groups (of voters).
The steps envisaged in the analysis of data vary depending on the types of study. If there
exists a set of clearly formulated hypothesis to start the study with, then each hypothesis can
be seen as a work prescribing a certain action to be taken vis-a- vis the data. The more
specific the hypothesis, the more specific the action. In such a study, the analysis is almost
completely a mechanical procedure. The task of analysis is reduced just to getting the
appropriate combinations of data and reading them off against the instructions for
verification and falsification of hypothesis.
Part of analysis is a matter of working out statistical distribution, constructing diagrams, and
calculating simple measures like averages, measures of dispersion, percentages correlation,
etc. Thus, statistical analysis form part of survey analysis. The case of complicated statistical
techniques in survey often stems up from the desire to establish and interpret multivariate
relationships. The analysis means verification of hypothesis. Under ideal conditions of
precision and simplicity, analysis presents very few problems since the statement of
hypothesis and the elaboration of the experimental design will automatically provide for the
analysis of the data.
6.6.3 Characteristics of Analysis of Data
Following are the main characteristics of data:
Analysis of data is one of the most important aspects of research, carried out by the
researcher himself or under his close supervision.
Data, facts and figures are silent and they never speak for themselves. It is through
systematic analysis that the important characteristics which are hidden in the data are
validly generalized.
86
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
The function of systematic analysis is to build an intellectual edifice in which properly
sorted, facts and figures are placed in their appropriate settings, and broader
generalizations beyond the immediate contents of the fact under study draw in up. So that
general inferences can be derived from them for showing consistent relation ships.
The data to be analyzed and interpreted should (i) be reproducible, (ii) be readily
disposed to quantitative treatment, and can serve as a basis for broader generalization
If the data are collected according to vague clues rather than according to the specific
hypothesis, in such cases the data are analyzed inductively or invested during the process
and not by means of any prescribed set of rules.
The task of analysis is incomplete with out interpretation. In fact analysis of data and
interpretation of data are complementary to each other. The end product of analysis the
setting up of certain general conclusions while the interpretation deals with what these
conclusions really mean.
Since analysis and interpretation of data are interwoven, the interpretation should more
properly be conceived of as a special aspect of analysis rater that a distinct operation.
Interpretation is the process of establishing relationship between variables which are
expressed in the findings and why such relation ship exists.
For any successful study the task of analysis and interpretation should be designed before
the data are actually collected with the exception of formulative studies where the
researcher had no idea as to what kind of answer he wants. Other wise there is always a
danger of being too late and the chances of missing important relevant data.
6.6.4 Statistical Methods in Analysis
Statistics is not merely for collecting numerical data but as a means of sound techniques for
their handling, analysis and drawing valid inferences from them. When the data are collected,
edited, classified, and tabulated, they are analyzed and interpreted with the help of various
statistical techniques and tools depending up on the nature of the investigation. Thus, the
basic knowledge about statistics becomes inevitable for research workers for systematic
analysis and accurate and precise interpretation of data.
A. Types of statistical methods
Statistical methods are the principles employed for the description, analysis and
interpretation of the data. They may be classified in to two categories, namely
87
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
I. Descriptive Statistical Methods
Those methods, which are employed primarily to describe what has been observed are called
descriptive statistical methods. Their role purpose is to describe the behavior of a variable
and no attempt is made to analyze and interpret the data. The data are collected, organized,
and presented either by tables or by diagrams to describe the behavior of the data.
II. Analytical Statistical Method
Those methods, which are employed to analyze and to interpret what has been observed, are
called analytical statistical method.
These two categories of statistical method are not mutually exclusive but analytical statistical
methods are based up on and make use of descriptive methods for analyzing and interpreting
data.
In some of the investigations, the sole purpose is to analyze and interpret what has been
observed rather than describing it, while in special studies conducted by government such as
population census per acre-yield etc., the data are collected and reported in order to describe
the situation and they are analyzed and interpreted to determine trends and possible future
developments.
III. Basic Statistical Techniques
While analyzing the data, researchers usually make use of many simple statistical devices
statistical methods widely employed with research data are the following.
a. Average
Average holds a very important place in all types of statistical work because they describe
the inherent characteristics of a frequency distribution in a concise manner and help in
comparative study of different distributions
Averages are of different kinds but we will consider five, namely, arithmetic mean, median,
mode, geometric mean and harmonic mean.
i.
Arithmetic Mean
Most widely used in statistical research because it is easy to understand and calculate. If the
measure of each item in a series is known, the mean can be derived by adding the measures
together and dividing by the number of items. In Economics it is used where all the items are
88
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
of equal importance. It takes in to consideration of all items from first to last and is
considered to be more representative.
The mean is simply the arithmetic average symbolized by M or X:
Where M= Mean
𝑁
M=
∑
E= Summation
xi
Xi= the ith score
____________
N= Total no of scores
N
ii. The Median
The Median is another simple average more frequently used where the extreme item is to be
eliminated. Medium is that value of variable which divides the group in to two equal parts,
one part comprising all the values greater and the other , all values tess than medium.
Thus the medium is the value of the variable which exceeds and is exceeded by the same
number of observations. It is very useful in the case of skewed (twisted) distribution such as
the distribution of in comes and wealth.
In short, the median refers to the middle value that divides a distribution in to two equal parts
when the scores are arranged in ascending or descending order.
For eg. 53, 57,
61
, ,61, 63
Median
48, 53,
57,61
61,63 hence, 57+61
=
59
2
iii. The Mode
In simple series the mode is the size of the measurement that occurs most frequently. In case
of frequency distribution it is the value of the variable corresponding to the maximum
frequency. It is very easy to calculate and understand. It can also be estimated graphically
from a histogram It is not at all affected by extreme observations and as such is preferred to
arithmetic mean while daring with extreme observations whenever complete data is not
89
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
available, mode is common form of average to be used. It is directly applicable to large
number of items. In this respect it is much superior to all other averages.
The mode is the most frequent or most common value in the distribution
A distribution of scores can be
 Unimodal- having only one mode. For the following distribution “21” is mode:
18,19,21,21,23,24
 Bimodal- having two modes. For the following distribution “12” and “18” are the
modes.11,12,12,12,14,16,18,18,21
 Hultimodal- Having three or more modes.
b. Geometric Mean
Geometric Mean is more mathematical and complicated than mean, median or mode.
Geometric mean of different items of a series is that root of the product of the item values as
there are items. In short, it is the root of the product of the item values. It is mostly used in
such cases where the data has to be put for further mathematical analysis. It is specially
suitable in those cases where less importance is to be given to large measurements. This will
be obtained by:M=
∑
xi fi
Where fi= frequency of the ith score.
____________
N
Consider the following distribution of scores on a test of 15 items for 34 students
Scpre (Xi)
Frequency (fi)
Xi X fi
Cumulative frequency
4
3
12
3
5
2
10
5
6
5
30
10
8
10
80
20
10
8
80
28
12
4
36
32
14
2
28
34
N=34
EXifi=276
90
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
The mean will be
M= 276/34 = 8.12
c. Harmonic Mean
It is reciprocal of the arithmetic mean of the reciprocals of the given observations. It is
rapidly defined, based on all observations and is amenable to further algebraic treatment. It
can be used in phenomena involving time, rate and price. It is most suitable average when it
is desired to give greater weight to smaller observations and less weight to the larger ones.
(N.B.: For Detailed and brief accounts of Basic statistical techniques, please refer S.
GUPTA’S “Research Methodology and statistical Techniques”
91
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
CHAPTER SEVEN
STYLE AND FORMAT OF REPORT WRITING
Report writing is a basic task of the researcher, since no research can be completed with out
its report, infact, a research without a report can be considered as a house with out roof. Any
amount of observation or data analysis would be in vain from the manager’s point of view, if
its report is not made available in aid of his decision-making process. Hence report writing
has a pivotal position in research.
7.1 Research Report
A research study culminates in the writing of a report, which is a tool for communicating the
various aspects of the study; the problem or topic investigated, the method employed to
investigate, the objective, scope and limitations. How ever, prior to writing the report, its
proper planning is essential. Report planning should take in to account such details as
defining the material collected, identifying the purpose of the report, etc. The ability to write
effective reports is one of the most useful skills a researcher can acquire. In this connection,
Briwn observes: We say it as simply as we possibly can, and this that is, that a report is a
communication from someone to another who wants to use that information. The report may
be elaborately formal it may be a letter,… it is simply memorandum; but it is always planned
for use,’’ The usefulness of a report is the chief aspect of any report writing. The report
identifies areas for further research, if any, and for fresh hypothesis. Analysis and inferences,
suggestions and observations, footnotes and appendices, etc; should also find a place in the
report. It should include specific recommendations for a course of action. While all the
necessary information materials should be presented in the most appropriate manner. It
should be purposeful and should take in to account the reader and his tastes and preferences
when it is written. In the normal course, the report writer should consider such questions as:
? - Who will read the report?
? – In what way is the report going to be useful?
? – What re the questions the report should answer?
?- How much information is needed?
? – What is the best way of presenting the information? and so on?
92
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
An effective report stimulates the interpersonal relationships in the given target area. In this
connection, Arthur D. Little observes; “… remember that the reader is a human being not
corporation. He is not omniscient; if he were, he wouldn’t have asked for your help.
Remember also that he doesn’t want to devote his whole career to deciphering what you have
to say. The project you are reporting on is undoubtedly only one of many that require his
attention. Your report should provide answers, not create more problems.
On the basis of presentation, reports may be classified as
-
Inductive reports;
-
Deductive reports;
-
Step-by-step reports;
-
Time sequence reports.

The Inductive Patterns of report writing is one of the olderst patterns of presenting ones
thoughts. Aristotle had pointed out long ago:” A whole is that which has a beginning,
middle, and an end.” This type of report goes from the specific – facts, figures, materials
of research – to general conclusions, summary, recommendations.
7.1.1. Conclusion
In this section, the conclusions are given based on the findings put in the summary section
discussed above. Findings (summary) state fact, while conclusions represent inferences
drawn from the findings. A writer is sometimes reluctant to make conclusions and leave the
task to the reader. Avoid this temptation when possible. As a researcher you are the one best
informed on the factor that critically influences the findings and conclusions.
The conclusions are the generalizations one makes from the findings, and contribute to the
body of knowledge. They must have one to one equivalence in answering basic questions
posed in the first chapter (proposal stage) and it is the past in which you give answer to your
basic questions.
In drawing conclusion, the researcher should make sure that the conclusion drawn is with in
the frame work of the study or data presented over under generalization should be avoided no
new data must be introduced at this stage and wordiness should be minimized.
93
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
7.1.2. Summary
In this section major highlights of the research findings, are given in a summarized form. The
summary is a brief statement of essential findings. Sectional summaries may be used if there
are many specific findings. These may be combined in an overall summary. In simple
descriptive research, a summary may complete the report, as conclusions and
recommendations may not be required.
The purpose of a summary is to provide the major findings on a nut shell. It should, thus
enable the reader understand the major findings of the study with out going to the details.
According to Galfo, Summarization is like a preparation of a perfume. It is the ways that
distill the essence from a large quantity of material without destroying or changing the
essence.
7. 1. 3. Recommendations
This part culminates the research Activity. Recommendations are meant to be suggestion by
way of providing solutions to the problem to the study. Recommendations should, however,
be feasible. They should take in to account objective reality of the situation. This should not
be unrealistic or high sounded . In academic research , the recommendations are often
further study suggestions that broaden or test understanding of the subject. Area. In applied
research the recommendation will usually be for managerial action rather than research
action. The writer may after several alternatives with justifications.
 The Deductive pattern of report writing is the most accepted type of report writing in the
business world. It is known as the executive report, the management report or the
action – getting report.
This is the pattern of presentation that goes from general to
specific, i.e. from the more important to the less important. It ends to become more
detailed or more specialized in its last pages because it is designed for a reader whose
fundamental questions “What do I need to know, to act or decide?” He wants to answer at
the very outset. The writer has a special obligation to think his way through to the central
issue or to the main point.
94
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
 A step – by –step presentation doesn’t follow any hard and fast rule, it simple presents
material blow-by – blow. It is a way of presenting the events or step in an operation
frequently following one another in a point of time. But the steps need not necessarily
come to a conclusion or an end.
 The time – sequence pattern of report writing is almost like that of the step-by-step
presentation; but it lays greater emphasis on the time element. It is an easy way of writing
a report by merely following the pattern the research material it self offers in a sequence
of time.
7.2 Steps in Report Writing
Many researchers find it difficult to make their research reports meaningful, though they toil
and moil to complete the project successfully. Many a time they lose heart when they start
their reports, because they realize that their effort is not up to the mark.
They may be task-maters, but they fail to complete their task. Some may be ‘good’
researchers, who may be painstaking but easy-going. They may keep on waiting until the
eleventh hour. In the process, their over confidence may be fatal to whole mission. At last
they are forced to complete a hotchpotch report.
Taking in to account all these realities, A few steps may be suggested, which would enable
the researcher to complete his task of writing a report clearly and cogently.
These steps are:
(i)
Plan the project well in advance; fix the target and the final data of completing the
project.
(ii)
The time for completing data collection and data processing should be well planned
and implemented.
(iii)
The time for report writing should be planned, and the task of report writing should
not be put off till the last minute. At least one –of the total project time should be
earmarked for this purpose.
(iv)
Select the structure for the report, arrange in groups of data, documents, bibliography,
etc., in conformity with structure of the research report.
(v)
Prepare an outline based on the structure, which should cover the main points in
detail.
95
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
(vi)
Prepare a rough point-by-point skeleton for each chapter theme, and crystallize the
report in a mental exercise
(vii)
In the event of any doubt, get it cleared by reading, thinking, recollecting and
discussing, before going farther.
(viii) Put the completed rough draft away for several days until you can bring a fresh mind
to bear up on it, and so on.
7.3 Format of the Research Report
A research report usually follows a fairly standardized pattern. The following out line
presents the usual sequence of various sections
7.3.1 Preliminary Section or Front Matter
-
Title page
-
Approval sheet
-
Acknowledgement (if any)
-
Abstract (preface)
-
Table of contents
-
List of tables(if any)
-
List of figures (if any)
7.3.2 Main Body of the Report
A. Introduction
-
Back ground of the study
-
Statement of the problem
-
Objective (purpose) of the study
-
Hypothesis or research questions
-
Significance of the study
-
Delimitations of the study
-
Limitations of the study
-
Definition of important terms.
B. Review of related literature or Analysis of previous Research
C. Design of the study (Research methodology)
-
Sampling techniques and procedures used
96
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
-
Data gathering methods and instruments used.
D. Presentation, analysis and Interpretation of data
-
Text
-
Tables
-
Figures
E. Summary/ Conclusion and Recommendation
- Brief Restatement of problem and procedures.
- Description of Procedures used.
- Principal findings and conclusions.
- Recommendations for alleviating the existing problem and/or attempts being made to use
the recommendations as a spring board for further research activities may be involved in
depth and breadth.
F. Reference Section
- Bibliography
- Appendix
- Index (if any)
7.4 How to Make Bibliography
For all projects that require literature review, a bibliography is necessary. Use the
bibliographic format required by the sponsor. If none is specified, standard styles that may be
used, including MLA style, APA style and Turabian style. Either of the three is correct. But
the question is keeping consistency in employing one and the same format amongst of these
through out your citation.
7.4.1
Form of the Bibliographic Entry
Three categories of information are needed for each bibliography entry: Author, title and
facts of publication such as time, place of publication and name of publisher. Each of
these categories may contain more than one peace of information. A book may have more
than one author and the facts for some materials may be complicated. A period follows each
category of information in a bibliography entry, i.e., a period follows the author, the title, and
97
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
the facts of publication. Because an entry in a bibliography (unlike an entry in a note) refers
to the complete work rather than to a specific passage. A bibliographic entry doesn’t include
page numbers A bibliography entry for an article lists the inclusive pages of the entire
article rather than specific pages from which material selected for action.
7.4.2
Books
The author for a book may include one or more authors, editors, compilers, and translators,
or a corporate author or institution. The title category includes the title and subtitle. The facts
of publication category identify the series in which the work appears the place (city) of
publication, the publisher and the year of publication.
 The name of the author for non-Ethiopian authors must be used as a sir name first
followed by a comma.
E.g., Santosdh Gupta is cited as:
Gupta, Santosh. 1993. Research Methodology and statistical Techniques. New- Delhi:
General Publishing House. Indian Research Association.
 Notice that the name of the author is inverted name, the title of the source martial
underlined and period marks used after the name of the author, the title and the publisher
excerpt the place of publication is followed by a collon.
E.g., 2 March, James G. and Herbert A. Simon. 1958. Organizations. Newyork:
Wiley
 The second example shows a two author citation
 Eg.3. Ebbit, Wilam R. and David, E. 1990. Writers Guide and Index of English.
(6th ed.). Glenview: scott. Forest man

The third example shows the inclusion of edition (if any) in the specific reference
source.
 When no authors name appears on a work or when the title page lists anonymous, then
the work is listed by title as:
E.g. . The Wind . Newyourk : Harper, 1995
 When the author is a group or corporation, then the publication is listed under the name
of the organization as:
98
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
E.g. . Hliday Magazine. Spain. Newyork : Random House,1994
 When the corporate author is also the publisher, the name does not need to be repeated
with the other facts of publication.
Eg., 6: Columbian University. The faculty Handbook Newyork, 1987.
 When a work has been edified, complied or translated by a person other than the author,
you have to decide under which name you should alphabetize the work, as:
E.g.,7 : Hayes, W.C. Most Ancient Egypt. Ed., Keith c.s Chicago: Univ. of chiacago
press. 1995.
 When you want to emphasize an article or chapter in the collection, palce the name of the
author of the article or chapter first. Titles of articles or chapters with in a book or journal
should be placed with in double coutation marks as:
E.g Miller, Arthur. “The playwright and the Atomic World.” In Theatre in the twenty
century. Ed., Robert, W.C.Newyork: Grove. 1963.
7.4.3
Title
The title of a book should appear in the bibliography exactly as it is on the title page.
Capitalization, however, may be changed. Any subtitle should be separated from the main
title with a colon followed by one space. In notes subtitles are optional, but is must appear in
the bibliography entry. The full title should be underlined.
E.g, 9: Walker, Ronald. Internal Pardise: Mexice and the Modern English
novel. Berkeley : Univ of California press, 1978.
Factors about publications: the facts of publication are the place of publication, the name of
the publishing house and the data of publication. The city name alone (wojt out the sate
name) may serve as the place of publication.
When a paper bound book is original edition, it is listed just as nay other book would be. But
when it is reprint of the original hand cover edition, the entry indicates the date of publication
of the hand cover edition. This information generally appears on the copyright (c) page.
99
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
7.5 Multivolume Works and Series
A multivolume work consists of two or more volumes under one general title. Each separate
volume may either have its own title or be identified by volume number only. When you wish
to refer to a complete multivolume work rather than to any specific volume, the bibliography
entry should include the total number of volumes and the inclusive dates of publication, if
applicable.
E.g.10 Bowsky, William. Ed. Studies in Medival and Renaissance History. 4 Voles.
Lincoln: Univ. of Nebreaska Press, 1963-67
7.5.1
Periodicals
Any publication that comes out at regular intervals is a periodical. Periodicals for an
academic or professional audience are usually called Journals; periodicals intended for the
general public are called magazines. The bibliography entry for periodical includes the
author’s complete name, the title of the article, and the facts of publication.
7.5.2
Journals
Most journals paginate continuously through each volume; the basic format for an entry
referring to such a continuously paginated is
E.g., 11 Aron, Raymond. “The education of the citizen in Industrial society”
Daedalus 91(1962): 249-63
7.5.3 Magazines
Issues of magazines are most often by data only, even when they have volume numbers. Page
numbers are separated from the data by a comma (rather than a colon, as in journal entries).
E.g. 12. Tuchman, Barbara. “ The Deline of Quality” Newyork Times Magazines,
2Nov.1980,38-57
7.5.4
News Papers
The bibliography raphy entry for a news paper should include the name of the (if available)
the news paper underlined
E.g., Rasky, Susa, Susa “ Senate Calls for Revision in New tax Health care”
Newyork Times 8 june 1998, A20
100
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)
Reference
1. Anderson, T.R. & Zelditch. Basic Cause in Statistical Methods. NewYork: Halt.
Rinchart & Winston, 1968.
2. Bajpai, S.R. Methods of Social Survey and Research. NewDdhi Ramputr Rampur,.
KitabGhar, 1960.
3. Connolly, T.G. & Sluckin, W. Introduction to Social Research and Statistical
Method. London: Cleave, 1957.
4. Dasputa, Sugate. Methodology of Social Science Research New De(hi)1987
5. Indian Council of Social Science l Research. Training Research Methodology in
Social Science. New Delhi:1971
6. Ggupta,S. Research Methodology and Statistical Techniques. NewDelhi: Indian
Commerce Association, 1982.
7. Kaufinan, Felix. Methodology of the Social Sciences. Humanities Press-1988
8. Lundberg, G.A. Socials Research: Study in Methods of Gathering Data. NewYork
:1979
9. Pande, G.C. Research Methodology in Social Sciences. Delhi: Anmol
Publications.1989.
10. Pellur, V.V. Marketing Research Theory and Practice. NewYork: McGraw Hill
Book company. Lowis, 1987
11. Tandon, B.C. Research Methodology in Social Sciences Allahabad: Chaitanya
publishing House. University Road, 1992
12. Westfall Boyd and Stasch. Marketing Research. Bombay: Himalayas Publishing
House. 1989
101
Copy © Rift Valley University College
Adama
Research Methodology (BUMA-331)