Dissertation Sessions 07-08
Primary Research Methods
Graham Pogson
High Mill 201
[email protected]
1
What Are We Covering Today?
• Quick review of research process
• Choice of primary research methods
• Questionnaires
–
–
–
–
–
–
–
–
–
Definition
Issues
Types
Development
Validity and reliability
Types of question
Data requirements table and exercise
Final stages in design
Administering the questionnaire
• Interviews
– Typologies
– Linkage to aims and objectives
• Observation
• Experiment
• Case study
• Ethics
See notes below slides
in the web version of
these slides
2
A Review of the Research Process
• The process appears linear but in practice a researcher
may visit and revisit each step several times:
– Aims and Objectives
– Literature Review (secondary research)
– Methodology
• Follows from and designed to fulfil aims and objectives
• Literature sources to be used
• Primary method(s) to be used
– Quantitative and or qualitative
• Analysis method(s) to be used on primary data gathered
–
–
–
–
Results gathered from primary data methods used
Discussion of results
Conclusions (including limitations of research)
Recommendations
3
Choice of Primary Research Method(s)
Figure 5.4
Research choices
Dependent
strands/phases
Independent
strands/phases4
Questionnaires
Saunders et al (2003) define questionnaire as a:
“General term including all data collection
techniques in which each person is asked to
respond to the same set of questions in a
predetermined order.” (p486)
• Issues to consider:
– Is a questionnaire the best option, is it the most
appropriate method for my aims and objectives?
– Evaluate all of the methods available (e.g. see below)
before you choose the questionnaire method
– “Questionnaires work best with standardised
questions that you can be confident will be interpreted
the same way by all the respondents”. Robson (2002)
in Thornhill et al (2003). They are not very good
when large numbers of open ended questions are to
be answered
5
Figure 11.1 Types of questionnaire
Administered by e-mail or website
The interviewer meets the interviewee face to face
and asks the defined schedule of questions
6
Questionnaire Development
The following is the order suggested for the
development of a questionnaire:
1. Aims and objectives
2. Methodology
–
Choice of questionnaire
3. Determine information required (objectives)
4. write questions to fulfil above and determine
question order
Order often used: 4, 3, 2, 1. This creates extra
problems!
7
Deciding What Data Need to be
Collected
• The validity and reliability of the data collected and the
response rate you achieve are dependant on
– The design of your questions, the structure of your questionnaire
and
– The rigour of your pilot testing
• The design of each question should be determined by
the data you need to collect and researchers do one of
the following:
– Adopt questions used in other questionnaires
– Adapt questions used in other questionnaires
– Develop their own questions
• Three types of data variable can be collected through
questionnaires:
– Opinion, e.g. “how do you feel about…..?”
– Behaviour e.g. “do…. put their customers’ interests before their
own”?
– Attribute, e.g. “how old are you?”
8
Validity and Reliability
Researcher is clear about the
information required and
designs a question
Researcher decodes
the answer in the way
the respondent intended
Respondent decodes the
question in the way the
researcher intended
Respondent answers
the question
9
Data Requirements Table
Research Question/Aim/Objective(s): establish consumers’
attitudes to alcoholic drinks in general, liqueur drinks and sloe gin in
particular.
Type of Research: (options are descriptive or explanatory)
Investigative
questions
Variable(s)
required
Detail in which
data measured
Yes or no
Do you consume
alcohol? (behaviour) How often
Yes or no
Number of times
per week, month,
year
Is the consumption
of alcohol good for
your health?
(opinion)
Very good to
very bad
5 points covering
extremes
Age? (attribute)
Age of
respondent
To nearest 5 year
band, youngest 15
oldest ?
Check
included in
questionnaire
√
Unresolved
point. Good
justification
for using this
table
10
Types of Question
• List: where the respondent is offered a list of items, any
of which may be selected
• Category: where only one response can be selected
from a given set of categories
• Ranking: where the respondent is asked to place
something in order
• Scale or rating: in which a rating device is used to record
responses
• Quantity: to which the response is a number giving the
amount
• Grid: where responses to two or more questions can be
recorded using the same matrix
See separate Word document for examples of the above
11
Other Factors to Consider
• Checklist for question wording
• Question coding
– for analysis
• Designing the form
– The order and flow of questions
– The layout of the questionnaire
12
Data Requirements Table Exercise
You are undertaking research on the use of
children's book clubs by householders
within mainland Europe. As part of this
you have already undertaken in-depth
interviews with households who belong
and do not belong to children’s book clubs.
This, along with a literature review, has
suggested a number of investigative
questions from which you start to construct
a table of data requirements:
13
Questions
1. For each investigative question listed, decide
whether you will need to collect data on
opinions, behaviours or attributes (circle o, b or
a)
2. Complete the table of data requirements for
each of the investigative questions already
listed (you may embellish the scenario to help
in your choice of variables required and how
the data will be measured as you feel
necessary)
14
Research Question/Aim/Objective(s): To establish mainland
Europe’s householders’ opinions about children’s book clubs
Type of Research: Predominantly descriptive, although wish to explain
differences between householders
Investigative
questions
Variable(s)
required
Detail in which
data measured
Check
included
in
question
naire
a. Do householders
think that children’s
book clubs are a good
or a bad idea? (o, b, a)
b. What things do
householders like most
about children’s book
clubs? (o, b, a)
c. How much do
households spend on
children’s books in a
year (o, b, a)
15
Research Question/Aim/Objective(s): To establish mainland
Europe’s householders’ opinions about children’s book clubs
Type of Research: Predominantly descriptive, although wish to explain
differences between householders
Investigative
questions
Variable(s)
required
Detail in which
data measured
a. Do householders
think that children’s
book clubs are a good
or a bad idea?(opinion)
Opinion about
children’s book
clubs
Very good, good,
etc. using a 5
point scale. Scale
or rating type
b. What things do
householders like most
about children’s book
clubs? (opinion)
What
householders like
about children’s
book clubs
e.g. prices, credit,
choice special
offers. Using a
ranking type
c. How much do
households spend on
children’s books in a
year (behaviour)
Amount spend on £0-10, £10-20 etc.
children’s books
Category question
by adults and
children per year
by household
Check
included
in
question
naire
16
Final Stages in Questionnaire
Design
• Explaining the purpose of the questionnaire
– The covering letter
– Introducing the questionnaire
– Closing the questionnaire
• Pilot testing and assessing validity
– Content validity: an expert commenting on
representativeness and suitability of your questions
will help here
– A trial run (pilot test) will help to ‘debug’ your
questionnaire. Aim for around 10 responses as a
minimum
• Testing for reliability
17
Administering the Questionnaire
The following are methods for distributing, completion and return of the
completed questionnaire.
• On-line: the questionnaire is attached to an e-mail or is completed
as a web page
• Postal: the questionnaire is posted to the respondent along with a
covering letter; several follow-ups may be required to ensure an
adequate response rate
• Delivery and collection: you deliver the questionnaire personally (or
your ‘agent’ does this) and negotiate completion date/time.
• Telephone: contact the respondents before time (e-mail, letter or
phone) so that they expect a call on a particular date/time
• Structured interviews: lots of factors of relevance here including
factors related to the interviewing process (see below)
The problems of administration are many and varied; do not expect a
100% response rate! See Chapter 10 of Saunders (2003) for details.
18
Interviews
An interview is “a purposeful discussion between
two or more people” Kahn and Cannell (1957) in
Saunders (2003)
Or:
“An interview is a conversation between two or
more people (the interviewer and the
interviewee) where questions are asked by the
interviewer to obtain information from the
interviewee. Interviews can be divided into two
rough types, interviews of assessment and
interviews for information.”1
1. http://en.wikipedia.org/wiki/Interview accessed 02 November 07
19
Figure 10.1 Forms of interview
And slides covering
questionnaires above
See next
slide for
details
20
Figure 10.2
Forms of electronic interview
21
Typologies of Interviews
There are several ways of dividing up interviews into types.
The following is one of the most common:
• Structured interviews: pre-determined and standardised
questions. C.F. questionnaires above
• Semi-structured interviews: the researcher has a list of
themes and questions, although these may vary from
interview to interview.
• Unstructured interviews: used to explore in depth a
general area in which you are interested. There is no
predetermined list of questions but you need to be clear
(aims and objectives) about what you want to explore
22
Linkage of Interviews to Aims and
Objectives
• Each type of interview as presented above has a
different purpose:
– Structured or standardised interviews can be used in
survey (questionnaire) research to gather data which
will then be the subject of quantitative analysis
– Semi structured and unstructured interviews are used
in qualitative research with emphasis on exploring the
‘why’ questions
• You may incorporate more than one type of
interview, for example using a structured
interview to determine the most important factors
to be explored in later semi-structured or
unstructured interviews (see slide 4 and notes
below slide)
23
Figure 9.1
Typology of participant observation researcher roles
24
Figure 5.2 A classic experiment strategy
25
Figure 7.1
Population, sample and individual cases
26
Figure 6.2
The nature of participant consent
27
Using a matrix in the planning of the content for the results
and conclusions chapters
Figure 14.1
28
References
Kahn, R. and Cannell, C. (1957) The
Dynamics of Interviewing, New York and
Chichester: Wiley
Robson, C. (2002) Real World Research, 2nd
ed., Oxford: Blackwell
Saunders, M. et al (2003) Research
Methods for Business Students, 3rd ed.,
Harlow: Pearson Education Limited
29
Download

Primary Research Methods - 07-08