Measurement Scales Measurement : The assignment of Numbers or other symbols to characteristics of objects according to certain pre-specified rules. Scaling: The generation of a continuum upon which measured objects are located. Primary Scales of Measurement There are 4 kinds of scales namely: Nominal scale Ordinal scale Interval scale Ratio scale Nominal scale In this scale numbers are used to identify objects. For example University Registration numbers assigned to students. Have you visited Bangalore? Yes-1, No-2 Yes is coded as one and No is coded as Two. The numeric attached to the answers has no meaning and is a mere identification. If the numbers are interchanged it wont affect the answer. Example for nominal scale The telephone number is a example of nominal scale where one number is assigned to one subscriber. Similarly bus route numbers are examples of nominal scale. “How old are you? This is an example of nominal scale. “What is your PAN Card Number? Arranging the books in the library subject wise, author wise Limitations There is no rank ordering. No mathematical operation is possible. Statistical implication- calculation of standard deviation and the mean is not possible Ordinal scale (ranking scale) The ordinal scale is used for ranking in most of market research studies. Ordinal scales are used to ascertain the consumer perceptions, preferences etc. This is also known as ranking scale Example of ordinal scale The respondents may be given a list of brands which may be suitable and were asked to rank on the basis of ordinal scale. Lux Liril Cinthol Lifebuoy Hamam Example for ordinal scale Rank item No of Respondents I Cinthol 150 II Liril 300 III Hamam 250 IV Lux 200 V Lifebuoy 100 Total 1000 Nominal scale- contd In the previous example II is the mode and III is the median. In market research the researchers often ask the respondents to rank the items like for example “A soft drink based upon flavor or Color”. In such cases the ordinal scale is used Interval scale Interval scale is more powerful than the nominal and ordinal scale. The distance given on the scale represents equal distance on the property being measured. Interval scale may tell us “How far object are apart with respect to an attribute?” This means that the difference can be compared. The difference between 1 and 2 is equal to the difference between 2 and 3. Eg for interval scale Eg 1: Suppose we want to measure the rating of a refrigerator using interval scale it will appear as follows: 1 Brand name Poor------------Good 2 Price High-------------Low 3 Service after sales Poor-----------Good 4 Utility Poor----------Good Interval scale-contd The researcher cannot conclude that the respondent who gives rating of 6 is 3 times more favorable towards the product under study than the respondent who awards the rating of 2. Eg 2: How many hours you spend to do class assignment every day? <3o min 3o min- 1 hr 1 hr- 1.5 hr 1.5 hr Difference between nominal and ordinal scale In nominal scale numbers can be interchanged because it serves only for the purpose of counting. Numbers in ordinal scale have meaning and it won’t allow interchangeability. Difference between interval and ordinal scale Ordinal scale gives only the ranking of the alternatives, one is greater than the other, but won’t give the differences/distances between one and other. Interval scales provide information about the difference between one and other. Ratio scale Ratio scale is a special kind of interval scale that has a meaningful zero point. With this scale, length, weight, or distance can be measured. In this scale it is possible to say, how many times greater or smaller one object is being compared to the other. Example: sales this year for product A are twice the sales for the same product last year. Statistical Implications: All statistical operations can be performed on this Difference b/w 4 Scaling Techniques Scale Characteristics Common Egs Marketing Egs Possible Statistics Des Inf Nominal Nos identify & Class objects SSN, Numbers of football players Brand Nos, Store Types %, mode Chi squar e Ordinal Numbers indicate the relative position of objects but not the magnitude of differences between them. Quality rankings, Ranking of teams in tournament. Preference Ranking, Market Position, Social Class. Percentile, median Rank order corrn , ANO VA Interval Difference between objects can be compared to zero point is arbitrary. Temperature (Fahrenheit, Centigrade). Attitude opinions Range, mean, S.D Prod uct mom ent corrn ,t test, ANO VA Ratio Zero point is fixed. Ratios of scale values can be computed. Length, weight. Age, Income, cost, sales, Market Share. Geometric Mean, H.M Coeff of Varia Classification of Scaling Techniques Comparative Scales: One of two types of scaling techniques in which there is direct comparison of stimulus objects with one another. There are 4 types of comparative scaling namely: Paired comparison Rank order Constant sum Q-Sort and other procedures. Classification of Scaling Techniques-Contd.. Non-comparative scales: One of the two types of scaling techniques in which each stimulus object is called independently of other objects in stimulus set. There are 2 types of Non-comparative scales namely: Continuous ranking scales Itemized ranking scales : consisting of three types namely: Likert Scale Semantic Differential Stapel Sampling A sample is a part of a target population which is carefully selected to represent the population. Sampling frame is the list of elements from which the sample is actually drawn. Actually sampling frame is nothing but the correct list of population. Example: telephone directory, product finder, yellow pages. Distinction between Census and Sample Census refers to complete inclusion of all elements in the population. A sample is a subgroup of the population. Sampling unit: If individual respondents form the sample elements and if we directly select some individuals in a single step, the sampling unit is also the element. That is both the unit and the element are the same. When Census is appropriate When the size of the population is small. Sometimes the researcher is interested in gathering information from every individual. Example: quality of food served in a mess. When Sample is Appropriate When the size of the population is large. When time and cost are the main considerations in research. If the population is homogeneous. Also there are circumstances when census is not possible Advantages of Sampling Sampling reduces time and cost of research studies. Sampling saves labor. The quality of study is often better with sampling. Sampling provides much quicker results. Sampling is the only procedure possible if the population is infinite. Statistical sampling gains a advantage over any other method. Limitations of Sampling Sampling demands through knowledge of sampling methods and procedures. When the characteristics to be measured occurs rarely in the population, a very large sample is required to secure units that will give reliable information about it. A complicated sampling plan requires more labor. Sampling Process It consists of seven steps: Define the population Identify the sampling frame Specify the sampling unit Selection of sampling method Determination of sample size Specify the sampling plan Selection of sample Types of Sampling Design Sampling is divided in to 2 types: Probability sampling Non-Probability sample Probability Sampling Probability sampling: In probability sampling, every unit in the population has a equal chances for being selected as a sample unit. The following are the characteristics: Every population has a equal chance of being selected. Such chance is known as probability. Probability sampling yields a representative sample. The closeness of a sample to the population can be determined by estimating the sample bias or error. Non Probability Sampling In the non probability sampling the units in the population have unequal or negligible , almost no chance for being selected as a sample unit. Its merits are as follows: It does not ensure a selection chance to each population unit The selection probability is unknown A non probability sample may not be a representative one. Non probability sampling plan does not perform inferential function. Probability Sampling Techniques Simple random sampling Stratified random sampling Systematic random sampling Cluster sampling Area sampling Multi-Stage and sub-sampling Non-Probability Sampling Techniques Convenience or accidental sampling Purposive or deliberate or (Judgment) sampling Shopping mall Intercept Sampling Sequential sampling Quota sampling Snowball sampling Panel samples Random Sampling Random sampling or simple random sampling is a process in which every item of the population has a equal probability of being chosen. There are 2 methods used in the random sampling A) lottery method B) using random number tables Advantages of Simple Random Sampling All elements in the population have an equal chance of being selected. Of all the probability sampling techniques simple random sampling is the easiest to apply. It is the most simple type probability sampling to understand. It does not require prior knowledge of true composition of the population. The amount of sampling errors associated with any sample can be easily computed. Disadvantages of simple random sampling It is often impractical because of non availability of population list. The use of simple random sample maybe wasteful if we fail to use all of known information. It does not ensure proportionate representation of various groups constituting the population. Systematic random sampling There are 3 steps: Sampling interval k determined by the following formula: K= No of units in the population/No of units desired in the sample One unit between the first and kth unit in the population list is randomly chosen. Add kth unit to the randomly chosen number Stratified random sampling A probability sampling procedure in which simple random sub-samples are drawn from within different strata, that are more or less equal on some characteristics. Stratified sampling are of 2 types: Proportionate stratified sampling Disproportionate stratified sampling Stratified random sampling- contd Sampling process is as follows: The population to be sampled is divided into groups (stratified). A simple random sample is chosen. Reasons for Stratified Sampling Marketing professionals want information about the component part of the population. Stratified sampling can be carried out with Same proportion across the strata proportionate stratified sample. Varying proportion across the strata disproportionate stratified sample. Cluster sampling The following steps are followed: The population is divided in to clusters. A simple random sample of few clusters is selected. All the units in the selected clusters are studied. The major advantage of cluster sampling is the case of sample selection. Cluster Sampling-Contd.. Clustering is done on the basis of geographical area Heterogeneity is secured within subgroups Homogeneity is secured between subgroups Random selection of subgroups or clusters is done. Cluster sampling process Identify clusters Examine the nature of clusters Determine the number of stages A) single stage B) two stage sampling C) multi stage sampling Area Sampling This is a probability sampling, a special form of cluster sampling. This is a important form of cluster sampling. In larger field surveys, clusters consisting of specific geographical areas like districts, taluk, villages, or blocks in a city are randomly drawn. As the geographical areas are selected as sampling units in such cases, the sampling is called area sampling. Area sampling-example If someone wants to measure sale of a toffee in a retail stores, one might choose a city locality and then audit toffee sales in retail outlets in those localities. The main problem in area sampling is the non -availability of lists of shops selling toffees in a particular area. Therefore, it would be impossible to choose a probability sample from these outlets directly. Thus the first job is to choose a geographical area and then list out the outlets selling toffee. Multi Stage Sampling The name implies that sampling is done in several stages. This is used with stratified/cluster design. In this method the sampling is carried out in 2 or more stages. The population is regarded as being composed of a number of first stage sampling units. each of them is made up of number of second stage units and so forth. That is at each stage, a sampling unit is a cluster of the sampling unit of the subsequent stage. Example of multi stage sampling The management of a newly opened club solicits membership. During the first rounds, all corporates were sent details so that those who are interested may enroll. Having enrolled, the second round concentrates on how many are interested to enroll for entertainment activities that club offers such as billiards, indoor sports, swimming and gym etc. after obtaining the information, we might stratify the interested respondents. This will also inform about the reaction of new members. Advantages and limitations of multistage sampling Advantages: It results in concentration of fieldwork in small areas. Savings in cost, time labor and money. Limitations: Procedure of estimating sampling error Cost advantage is complicated. Sub sampling Sub sampling is a part of multi stage sampling process. In multistage sampling the sampling in second and subsequent stage frames is called sub sampling Non-Probability Sampling Convenience or Accidental Sampling • This is a non-probability sampling • It means selecting a sample units in a just hit and miss fashion, example: interviewing people whom we happen to meet. • This sampling also means selecting whatever sampling units are conveniently available. • Example: A teacher may select students in his class • This is also known as accidental sampling because the respondents whom the researcher selects are accidentally included in the sample. Advantages and Limitations Advantages: Cheapest and simplest method It does not require list of population It does not require any statistical expertise Limitations: Highly biased Least reliable sampling method The findings cannot be generalized Purposive or Deliberate Sampling This is also known as judgment sampling The investigator uses his discretion in selecting sample observations from the universe. This method involves selection of cases which we judge as the most appropriate ones for the given study. The investigator chooses the sample that may be true representative of the universe. Purposive Sampling-Contd.. Example: Test market cities for the launch of an new product is being selected on the basis of judgment sampling, because these cities are viewed as typical cities matching with certain demographic characteristics. Example: A researcher may deliberately choose industrial undertakings in which quality circles are believed to be functioning successfully and undertakings in which quality circles are believed to be total failure. Advantages and limitations-Purposive Sampling Advantages: It is less costly and more convenient. It guarantees inclusion of relevant elements in the sample. Limitations: It does not ensure Shopping mall intercept sampling This is a non probability sampling method. In this method the respondents are recruited for individual interviews at fixed locations in shopping malls. This type of study would include several malls each serving socio economic population. Merits and Demerits-Shopping Mall Intercept Merits It has relatively small universe It is expected to give quick results. The level of accuracy can vary from the prescribed norms. Demerits: It allows bias Subjectivity of the enumerator. Sequential sampling This is a method in which the sample is formed on the basis of series of successive decisions. They aim at answering the research question on the basis of accumulated evidence. Example-Sequential Sampling Assume that a product needs to be evaluated. A small probability sample is taken from among the current users. Suppose it is found that the average annual usage is between 200 and 300 units. It is known that the product is economically viable only if the average consumption is 400 units. This Information is sufficient to take a decision to drop the product. On the other hand if the initial sample shows a consumption level of 450 to 600 units additional samples are needed for further studies. Quota Sampling Quota sampling is quite frequently used in marketing research. It involves the fixation of certain quotas which are to be fulfilled by the interviewers. Suppose 2,000 students are appearing for competitive examination. We need to select 1% of them based on quota sampling. The classification of quota may be as follows. Classification of samples category General merit quota 1000 sports 600 NRI 100 SC/ST 300 Total 2000 Steps in quota sampling The population is divided in to segments on the basis of certain characteristics. Here the segments are termed as cells. A quota is selected from each cells. Limitations-Quota Sampling It may not be possible to a representative sample within quota. Because of too much liberty to the interviewers the quality of work suffers. Panel samples Panels are frequently used in marketing research. Example: suppose that one is interested in knowing the change in the consumption patterns of household. A sample of households are drawn. These households are contacted to gather information on the pattern of consumption. Subsequently may be after a period of six months the same households are approached once again and the necessary information on their consumption is collected. Errors in sampling Sampling error Non sampling error Sampling frame error Non response error Data error Sampling error The only way to guarantee the minimization of sampling error is choose the appropriate sample size. As the sample keeps increasing the sampling error decreases. Sampling error is the gap between sample mean and the population mean. Non sampling errors non sampling errors occurs in some systematic way which is difficult to estimate. A sampling frame error occur when list of population is not sufficient. Other sampling errors Non response errors occurs because the planned sample and the final sample vary significantly. Data errors occurs during data collection analysis of data or interpretation. Respondents sometimes give distorted answers unintentionally for questions which are difficult, or the question is exceptionally long and the respondent may not have answer. Data errors also occurs because of the physical and social characteristics of the interviewer and the respondent. Sample size Determination-Symbols Sampling Distribution: The distribution of the values of a sample statistic computed for each possible sample that could be drawn from the target population under a specified sampling plan. Statistical Inference: The process of generalizing the sample results to the population results. Normal Distribution: A basis for classical statistical inference that is bell shaped and symmetrical in appearance. It measures the central tendency are all identical. Standard Error: The Standard deviation of the sampling distribution of the mean or proportion. Statistical Approach to determining Sample Size The Confidence Interval Approach Sample size determination: Means Sample Size Determination: Proportions Adjusting the statistically determined Sample Size. Module 3-Field Procedures In the data gathering, stage there are 2 primary objectives. Maximizing the relevant information that is elicited from the people providing it. (and who confirm to the sampling specification). Minimizing errors which are of numerous varieties and occurs easily. Constraints in Field work The researcher must operate under some serious constraints such as: Time Money Environment Field procedures for Data Collection Methods Observation: observers act in 2 quite different capacities . One is that of obtaining information that is already recorded or deals with objects that are fixed in nature over some period (that is nonbehavioural). Some of the more prevalent records such as financial statements, economic data, and content analysis of competing advertising. Another form, physical condition analysis, involves the field personnel obtaining sales data on concerned brands through a store audits of the incoming merchandise records and counts of inventory on hand. Facts on prices, displays, and shelf facings might also be noted in the study to determine competitive conditions. Observation plans can specify the details of who, what when, where, and how to observe an object or individual. Field procedures for Data Collection Methods-Contd.. The other capacity of observers is that of perceiving and recording people’s behavior. This form of observation can be classified into 4 major categories: Nonverbal behavior, which includes body movement, motor expressions, and glances. Linguistic behavior, which involves the study of presentation content, or what, how, and how much information is conveyed in a particular situation. Extra linguistic behavioral dimensions including vocal (Pitch, loudness,) temporal (rate of speaking, duration and rhythm), interaction (Tendencies to interrupt, dominate or inhibit), verbal stylistic (Vocabulary, pronunciation, and dialect). Spatial relationship: which involves how one relates physically to others , such as maintaining appropriate distances between oneself and others. Observation Plans It specifies details of : Who? The researcher must give the observer the specifications that would qualify a subject to be observed. What? The basic unit of observation must be defined so the observer will know what to record. For example, should the observer record an expressed thought, a physical movement, a transaction, a facial expression, a particular behavior or what. When? If time is an important factor to the study, then the observer must be told when to observe. He or she can be directed to observe on a particular day or during a particular week. Or the observer will be instructed to observe during a particular period of time, say every 30 minutes of each hour. Where? The observer must be told where to observe. Field observation tends to be in the natural settings, but the observer must be directed to appropriate store, street, a particular asile within a store and so forth. How? The observer must be instructed on how they are to observe the subject. That is, whether the presence of the observer should be made known to the subject. On the other hand, some situations may require the observers to be hidden Personal Interviewing In this method, of Personal Interface between Interviewers and respondents, there tends to be the greatest opportunity for gathering abundant information. It also offers the widest range of interviewing techniques. On the other hand it is the most expensive and time consuming method and is sometimes the most fraught with error potentialities. Tasks in Personal Interviewing It Involves 5 extensive tasks, which is summarized as below: Fulfill the sampling plan by covering the designated areas or locations and reaching the designated persons. Administer the questionnaire in strict accordance with instructions. Record the responses precisely as given, in terms of the measurements that are called for by instructions. Return the information to the central point of editing and data processing by the stipulated time. Complete the field work within budgeted cost. Here the first 4 tasks fall entirely on the interviewer, and the fifth needs his or her cooperation. Personal Interviewing- Contd.. Interviewing essentially is an interpersonal process in which one person (i.e. the Interviewer) endeavors to elicit data or attitudinal responses from another person (the respondent). After establishing sufficient rapport, or level of understanding with the respondent, the interviewer offers a stimulus-usually a question- to obtain a response that provides the needed data. Upon receiving the response, the interviewer must interpret it in a number of ways. Surveys differ widely in their demands on the interviewer. When the interviewer can obtain the needed information with complete structuring (employing only standardized questions), there is a little reliance on the interviewer’s ability to the direct the communications. In many instances, where probing or formulation of appropriate question on the spot is needed to obtain full or appropriate information, however greater reliance is placed on the interviewer’s intelligence, dependability, and grasp of the study’s objectives. Personal Interviewing- Contd.. Business and professional interviews on matters relative to a trade, profession, or industry (for example, surveying doctors on medical matters), may place the interviewer in more difficult role. Sometimes they involve technical terms or jargons and considerable understanding of the interviewee’s field or profession. They may be more demanding also in that the most valuable business and professional surveys are unstructured, so that the formulation of questions devolves on the interviewer. The group or focus interview is one in which six or eight persons are going to be interviewed together and in a free wheeling discussions rather than answering a structured questionnaire. In this situation, one clearly faces quite different interviewing procedures than under the contrasting situation of interviewing a person individually. Personal Interviewing- Contd.. The unstructured characteristics of group interviewing makes it similar to informal or depth interviewing of a single person, a somewhat clinical psychological method, that is not included in our coverage techniques. This means, the interviewer is not limited to certain concretely stated questions, but rather has latitude to compose and phrase questions as the interview proceeds. Telephone Interviewing In this medium of communication there is only a vocal interface between interviewer and the respondent. The tasks of telephone interviewing are somewhat modified from those that we described for personal interviewing , so our list is as follows: Call the telephone numbers listed in the sampling plan. Ask for the person designated in the plan. When the person is reached, administer the questionnaire in strict accordance with the instructions. Turn over the completed questionnaire to the personnel who will edit it and prepare it for data processing. Telephone Interviewing-Contd.. The telephone interviewer does not have the effort of legwork to find respondents and can easily dial callbacks in attempting to reach those not at home. Telephone usage in surveys has been rising for at least a decade and is now one of the most used techniques. Telephone surveys now tend to be made from a central point, often the national office of the survey agency. Interviewing methods by telephone do not differ greatly from those that are appropriate face to face. Rapport with the person interviewed must be developed unseen, with everything resting on the friendliness of the voice and what is said. The interviewer must be well prepared to keep the interview moving steadily, because it is much easier to lose a respondent over the phone than when in his or her prescence. Techniques of Telephone Interviewing Random Digit dialing: It enables the researcher to access all working telephones regardless of whether their numbers are published in directories. Several methods have been developed, that include choosing phone numbers by using random digit dialing, with or without the computer. Computer assisted telephone interviewing: The telephone interviewer sits at a table in front of a CRT console, which has a television like screen that displays questions, answers, and directions for conducting an Interview. Mail Surveys In this medium of data collection there is no field worker and no personal interface of course for communication. Instead, the respondent is reached by a postal carrier, an impersonal contact. The absence of an intermediary, the interviewer does make the communication direct and simpler, but the field work of mail surveys is equally challenging. All the functions are shifted to persons in some central office locations, whose tasks are of these types: Compile or purchase address lists of the desired kinds of respondents who are located within the sample areas. Address envelopes, stuff them with the questionnaire and other materials and mail them. To those not responding by selected cutoff date, mail follow-up and questionnaires. (when those who responded cannot be identified, follow-up mailings should be sent to the entire original mailing list). Edit the questionnaires, returned and prepare them for data processing,. Mail Surveys-Contd.. The problems peculiarly associated with mail surveys stem largely from supervising the various tasks namely, overseeing the assistants who perform and record these routine activities. One aspect of researcher’s supervision entails his or her close attention to the assistants who are preparing the survey materials for mailings. The researcher must make sure that each envelope contains the proper number of items (questionnaires, covering letter, incentive, return envelope etc. The other aspect of researcher’s supervision concerns detailed record keeping. Once the questionnaires are mailed (Usually should be mailed at one time), the researcher should keep track of the response trends. Also, the researcher should request a dated receipt from the post office indicating the number of envelopes mailed as a evidence of original sample size. Success in the mail surveys depends on 2 aspects: The questionnaire and its covering messages and instructions. The researcher’s supervision. Error Sources in Field Work The twin objectives of field work are to: Maximize the flow of pertinent , accurate data. Minimize the errors committed by the Interviewers. Sources of Errors Respondent Selection error Non-response errors Communication errors Respondent Selection Error This kind of errors may be made in selecting sample members: Obtaining information in the wrong place. Obtaining information from the wrong person. Omitting information from persons who were supposed to be interviewed in the sample design. Among the three media of communication (personal, mail, telephone), the likelihood of these kinds of errors varies. Non-response Errors Non-response are the most common field sampling errors. These results primarily from: Failure to reach the intended respondents because they are available or because there has not been an effort to reach them or Persons reached do not provide the requested information. The first problem is the worse, due to not at homes. Communication errors In the interpersonal process of question and answer, numerous possible errors, can be made by the interviewer or person whom he or she is interrogating. Trouble may first arise in the effort to obtain proper rapport with the interviewee. Interviewing errors may also stem from failure to follow instructions in administering a questionnaire. The interviewee may not receive a proper explanation of the survey’s natureor may receive one in a manner that would bias responses. Another type of interviewing error is categorized as “omissions”. Finally erroneous responses form another interviewing problem. .. Communication errors- Contd The other communication errors may be such as: Recording errors Falsification Managing the field work There are 6 Phases in Managing field work: Pretesting Simplifying procedures. Interviewer recruitment and selection. Instructing the field workers. Supervision control Phases of Field work Pretesting: Pretesting of every important project should be a standard procedure. Minor and repetitive projects may be conducted without pretests or with a quick testing of a questionnaire on some convenient subjects. An adequate pretest is much more than that, for it applies the complete methods of data collection to a sample of persons similar to those specified for the full study. Pretest may reveal to those directing the gathering of primary data, various planning errors that otherwise would have gone unnoticed. Errors frequently result from what the interviewer is requested to do rather than from mistakes on the part of interviewer or the person interviewed. Phases of field work- Contd.. Simplifying Procedures There are a number of efficiencies that may be utilized to simplify field work tasks. Some illustrations are given below, which does apply to all types of survey. The interviewer may be equipped with cards or pages to be handed over to interviewees, to clarify or illustrate desired responses or to introduce the interviewer and thereby help to establish rapport. Diagrams of rating scales, pictures, statements in multiple choice questions, and desired categories of response are other examples of such handouts. The self-administered interview may substitute for having the interviewer ask the questions. The interviewee may complete his or her answers while the interviewer waits, or the latter may call back to retrieve the answers at some specified time. Tape recording of interviews obviously enhances the fidelity of recorded responses and eases the interviewer’s role. Previous appointment usually by telephone tends to increase the number of completed interviews per personal visit. Various ways of improving the design and legibility of questionnaires may be applied to easing the work and enhancing accuracy. Phases of field work-Contd.. Interviewer Recruitment and selection The data collection process in which interviewers are entrusted to gather the data is a crucial stage in the research process. The research project will be no better than the data gathered in the field by the interviewers. Interviewer error is of significant concern. Some of the characteristics taken into consideration include the following: Education: Interviewers must have reasonably good reading and writing skills. Gender: In most cases women are recruited for interviewing positions. Voice quality: The voice of the interviewer must be such that it is free of any heavy accents, harshness or features that could be irritating. Experience: An advantage of hiring experienced interviewers is that they are likely to do a better job at the following instructions, obtaining respondent co-operation, being able to record accurately, and guiding respondents through the interview in a smooth and flowing manner. Phases of field work-Contd.. Instructing field workers: Instructions should be stated in clear and distinct terms, of course and should cover these topics : What the survey is about When the survey is to start and when it is to be finished. How many persons are to be interviewed, where and how to select them, and what to do about persons not at home. How to introduce oneself and initiate the interview. How each question should be asked and which ones contingent on the answers to other questions. Methods of probing, encouraging responses and aiding memory. If any items are to be observed, what is to be noted. How each questionnaire is to be studied and corrected before returning the form. What to do with completed questionnaires. When and how the interviewer will be paid for his/her work. The exact basis on which the quality of work will be appraised. Phases of field work-Contd.. There are four basic method s to teach the interviewer: Written materials are used. Lectures and demonstrations Role plays Field practice Phases of field work- Contd.. Supervision Interviewers should be under a field supervisor whose duties would include: Training, assisting and overseeing Mapping, and prelisting addresses for the specific sample selection in the field. Hiring local interviewing help. Editing the questionnaires turned in before forwarding them to the central office. Phases of field work-Contd.. Supervision The key to good supervision is acquiring the needed information to evaluate an interviewers performance. The interviewer can be evaluated on several factors such as: Costs Response rates Quality of data Quality of interviewing Control Good control hinges on having realistically anticipated and planned a survey, with the plan written in detail so that its execution can be followed closely. Two other steps that are instrumental in achieving control are scheduling and validating. Field-work Data Collection Process Selection of field work Training of field workers Supervision of field workers Validation of field work Evaluation of field work. Field work- Process Selection of Field workers: here the researcher should Develop job specifications for the project, taking into account the mode of collecting data. Decide what characteristics the field workers should have. Recruit appropriate individuals. Interviewers background, characteristics, opinions, perceptions, expectations, and attitudes can affect the responses they elicit. Field work Process- Contd.. Training the field workers: it should cover: Making the initial contact Asking the questions Probing: helps the respondent to focus on specific content of the interview. Some of the techniques of probing are repeating the questions, repeating the respondents reply, using a pause or silent probe, boosting or reassuring the respondent, eliciting clarification, using objective questions. Recording the answers Terminating the interview. Field work Process- Contd.. Supervision of field workers: Involves Quality control and editing Sampling control: attempts to ensure that the interviewers are strictly following the sampling plan rather than selecting the sample based on convenience or accessibility. Control of cheating. Field work process-Contd.. Validation: of field work means verifying that the field workers are submitting authentic interviews. Evaluation of field workers: is based on the following creteria: Cost and time Response rates Quality of interviewing Quality of data. Tabulation Tabulation refers to counting the number of cases that fall in to various categories. The results are summarized in the form of statistical tables. The raw data is divided in to groups and sub-groups. The counting and placing of data in a particular group and subgroup are done. Tabulation-contd.. The tabulation involves: Sorting and counting Summarizing of data Tabulation may be of 2 types: Simple tabulation Cross tabulation Types of tabulation In simple tabulation a single variable is counted. Cross tabulation involves 2 or more variables which are treated simultaneously. Tabulation can be done entirely by hand or by machine, or by both hand and machine. Tabulation- Contd.. The form in which tabulation is to be done is decided by taking in to account: The purpose of study The use of statistical tools E.g. mean, mode, standard deviation etc. Improper tabulation may create difficulties in the use of these tools. Sorting and counting data Sorting by manual method is as follows: Sorting of data Income 1000 1500 2000 2500 tally marks IIII/ IIII/ III IIII/ IIII/ II IIII/ IIII/ IIII/ I frequencies 5 8 12 16 Tabulation-Contd.. The tabulation may include table number, title, head note, sub caption, sub-entries, body of the table, footnote and the source. The following example explains the component of a table. Format of a blank table TITLE- number of children per family Head Note- Unit of Measurement Sub heading Caption Body Foot note Total Tabulation-Contd.. The table must have a clear and brief title. The head note, usually the measurement unit, is placed at the top of the table in the right hand corner in a bracket. Stub indicates the row title or the row headings and is placed in the left-hand column. Caption indicates what each column is meant for. Kinds of Tabulation 1) Simple or one-way tabulation: The multiple choice question which allows only one answer may use one tabulation or univariate. The questions are predetermined and consists of counting the number of responses falling into particular category and calculate the percentage. Types of univariate tabulation Question with only one response Multiple responses to question Question with one response: if the question has only one answer the tabulation may be of the following type: Table 1 study of no of children in a family No of children o 1 2 3 4 More than 4 family 10 30 70 60 20 10 200 percentage 5 15 35 30 10 5 100 Question with multiple response Sometimes respondents may give more than one answer to a given question. In this case, there will be an overlap, and responses when tabulated, need not add to 100 percent. Table 2 choice of an automobile Parameter No of respondents Engine 10 Body 15 Mileage 15 Interior 06 Colour 18 Maintenance frequency 16 Inconvenience 20 E.g.-Contd.. There is duplication because respondents may be dissatisfied with the mileage given by the vehicle and may dislike interior of the car. Here there are more than one parameters to dislike the car by the owner. Tabulation of cause of inconvenience felt by car owners It can be classified as follows: Cramped legroom Rear seat problem Difficulty in raising the window Difficulty in locking the door. Now the tabulation of each of the specific factors would help to identify the real reasons for dislike Cross tabulation or 2 way tabulation This is known as bivariate tabulation. The data includes 2 or more variables. Cross tabulation is very commonly used in market research. The usefulness of cross tabulation is indicated with the example which is as follows: Table 3 use of health drink Income per month 0 1 2 3 4 5 More than 5 No of families <1000 5 0 8 9 11 15 25 73 10012000 10 5 8 10 13 18 27 91 20013000 20 10 12 14 20 22 32 130 30014000 12 3 6 7 13 20 30 91 40015000 6 2 6 5 10 15 20 64 >5000 6 1 4 5 7 10 18 51 59 21 44 50 74 100 152 500 E.g.-Contd.. The above table shows that consumption of a health drink not only depends on income but also on the number of children per family. Health drinks are also popular among the family with no children. This shows that even adults consume this drink. It is obvious from the table that 59 out of 500 families consume health drinks even though they have no children. The table also shows that families in the income group of 2001-3000 consume health drink the most. Module-4- Data Analysis Multivariate analysis This can be studied under: Discriminant analysis Factor analysis Cluster analysis Conjoint analysis Multidimensional scaling Discriminant Analysis In this analysis 2 or more groups are compared. In the final analysis, we need to find out whether the groups differ one from another. Example of discriminant analysis Where discriminant analysis is used: Those who buy our brand and those who buy competitors brand. Good salesman and poor salesman, medium salesman. Those who go to food world to buy and those who buy in a kirana shop. Heavy user, medium user and light user of the product. Equn for discriminant analysis Z= b1x1+b2x2+b3x3……… Z= Discriminant score B1=Discriminant weight for variable 1 B2= Discriminant weight for variable 2 B3= Discriminant weight for variable 3 X=Independent variable Application of discriminant analysis A company manufacturing FMCG products introduces a sales contest among its marketing executives to find out “How many distributors can be roped in to handle the company’s product”. Assume that this contest runs for 3 months. Each marketing executive is given a target regarding number of new distributors and they can generate during the period. This target is fixed and based on the past sales achieved by them about which, the data is available in the company. Application of discriminant analysis-Contd.. It is also announced that the marketing executives who add 15 or more distributors will be given a maruti omni-van as prize. Those who generate between 5 and 10 distributor will be given a 2 wheeler as prize. Those who generate less than 5 distributor will get nothing. Now assume that 5 marketing executives won a maruti van and 4 won a 2 wheeler. Application of discriminant analysis-contd.. The company wants to find out, which activities of the marketing executive made the difference in terms of winning a prize and not winning the prize. One can proceed in a number of ways. The company could compare those who won maruti van against others. Alternatively the company might compare those who won, one of the 2 prizes, against those who won nothing. Application- contd.. Discriminant analysis will highlight the difference in activities performed by each group members to get the prize. The activity might include: More number of calls made to the distributors. More personal visits to the distributors with advance appointments. Use of better convincing skills. Conducting Discriminant Analysis The steps involved in conducting Discriminant Analysis is as follows: Formulate the problem Estimate the discriminant function coefficients. Interpret the results Assess the validity of discriminant analysis Factor analysis The main purpose of factor analysis is to group large set of variable factors into fewer factors. Each factor will account for one or more component. Each factor a combination of many variables. Factor analysis model Mathematically, factor analysis is somewhat similar to multiple regression analysis, in that each variable is expressed as a linear combination of underlying factors. Factor Analysis Model- Contd.. If the variables are standardized, the factor model may be represented as: Xi=Ai1F1+Ai2F2+Ai3F3+……..+AimFm+ViUi Where Xi= ith Standardized variable Aij= standardized multiple regression coefficient of variable i on common factor j. F=Common Factor Vi= standardized regression coefficient of variable i on unique factor i. Ui= the unique factor for variable i. M= number of common factors. Statistics associated with factor analysis Bartlett’s test of sphericity: is a test of statistics used to examine the hypothesis that the variables are uncorrelated in the population. In other words, the population correlation matrix is an identity matrix. Correlation matrix: A correlation matrix is a lower triangle matrix showing the simple correlation, r between all the possible pairs of variables included in the analysis. Communality: is the amount of variance, a variable shares with all the other variables being considered. This is also the proportion of variance explained by the common factors. Eigen value: represents the total variance explained by each factor. Statistics associated with factor analysis- Contd.. Factor loadings: are simple correlations between the variables and the factors. Factor loading plot: A factor loading Plot is the plot of original variables using the factor loadings as coordinates. Factor matrix: A factor matrix contains the factor loadings of all the variables on the factors extracted. Factor scores: Factor Scores are composite scores estimated for each respondent on the derived statistics. KMO: Kaiser Meyer Olkin measure of sampling adequacy: is an index used to examine the appropriateness of factor analysis. High values between 0.5 and 1.0 indicate factor analysis is appropriate. Values below 0.5 imply that factor analysis may not be appropriate. Statistics associated with factor analysis- Contd.. Percentage of variance: This is the percentage of the total variance attributed to each factor. Residuals: Residuals are the differences between the observed correlations, as given in the input correlation matrix, and the reproduced correlations, as estimated from the factor matrix. Scree plot: A scree plot is a plot of the eigenvalues against the number of factors in order of extraction. Conducting factor analysis The steps involved in conducting factor analysis is as follows: Formulate the problem Construct of correlation matrix. Determine the method of factor analysis. Determine the number of factors. Rotate the factors. Interpret the factors: calculate the factor scores, select the surrogate variables. Determine the model fit. Conducting factor analysis- Contd.. Principal component analysis: An approach to factor analysis that considers the total variance in the data. Common factor analysis: An approach to factor analysis that estimates the factors based on the common variance. Conducting factor analysis- Contd.. Determine the number of factors: The number of factors can be determined using the following approaches: A priori determination. Determination based on Eigen values. Determination based on scree plots. Determination based on percentage of variance. Determination based on split-half reliability: The sample is split in half and factor analysis is performed on each half. Determination based on significance tests. Conducting factor analysis- Contd.. The rotation of factor can be done based on; Orthogonal Rotation: Rotation of factors in which the axes are maintained at right angles. Variance procedure: It is a commonly used procedure. An orthogonal method of factor rotation that minimizes the number of variables with high loadings on a factor, thereby enhancing the interpretability of the factors. Oblique rotation: Rotation of factors, when the axes are not maintained at right angles. Factor analysis –contd.. There are 2 most commonly employed factors analysis procedures. They are: Principle component analysis Common factor analysis When the objective is to summarize information from a large set of variables in to a few factors, principle component factor analysis is used. On the other hand if the researcher wants to analyze the components of the main factor, common factor analysis is used. Example of common factor analysis Example: inconvenience inside a car. The components may be: Leg room Seat arrangement Entering the rare seat Inadequate dickey space Door locking mechanism Example of principle component factor analysis Example: customer feedback about a 2 wheeler manufactured by a company. The MR Manager prepares a questionnaire to study the customer feedback. The researcher has identified 6 variables or factors for this purpose. e.g for principle factor analysis- contd.. The factors are as follows: Fuel efficiency (A) Durability (B) Comfort (C) Spare parts availability (D ) Breakdown frequency (E) Price (F) Factor analysis- contd.. The questionnaire may be administered to 5000 respondents. The opinion of the customer is gathered. Let us allot points 1 to 10 for the variables factors A to E. 1 is the lowest and 5 is the highest. Let us assume that the application of factor analysis has led to grouping the variables as follows. Factor analysis- contd.. A, B, D,E into factor 1 F into factor-2 C into factor-3 Factor-1 can be termed as technical factors Factor-2 can be termed as Price factor. Factor-3 can be termed as Personal factor. Applications of factor Analysis It is used for market segmentation. Product research: can be employed to determine the brand attributes that influence the consumers choice. Advertising studies: media consumption habits of target audience. Pricing studies: to identify characteristics of price sensitive consumers. Cluster Analysis Cluster analysis is used to: To classify persons or objects into small number of clusters or groups. To identify specific customer segment for the company’s brand. Cluster analysis is a technique used for classifying objects into groups. This can be used to sort data( a number of people, companies, cities, brands or any other objects) into homogenous groups based on their characteristics. Applications of Cluster Analysis Customer segmentation Estimation of segment sizes Industries where this technique is useful includes Automobiles Retail stores Insurance B to B Durables and packaged goods VALS (consumer Behavior) Statistics associated with cluster Analysis Agglomeration schedule: An agglomeration schedule gives information on the objects or cases being combined at each stage of the hierarchical clustering process. Cluster centroid: Is the mean values of the variables for all the cases or objects in a particular cluster. Cluster membership: Indicates the cluster to which each case or object belongs. Dendrogram: A Dendrogram or tree graph is a graphical dev ice for displaying clustering results. Distances between cluster centers: These distances indicate how separated the individual pairs of clusters are. Icicle diagram: An icicle diagram is a graphical display of clustering results, so called because it resembles a row of icicles hanging from the eaves of the house. Similarity/distance coefficient matrix: Is a lower triangle matrix containing pair wise distances between objects or cases. Conducting Cluster Analysis Formulate the problem Select a distance measure Select a clustering procedure Decide on the number of clusters Interpret and profile clusters. Assess the validity of clustering. Select a clustering Procedure Hierarchical Clustering: A Clustering procedure characterized by the development of hierarchy or tree like structure. Agglomerative clustering: hierarchical clustering procedure where each object starts out in a separate cluster. Divisive clustering: Hierarchical clustering procedure where all the objects start out in one giant cluster. Clusters are formed by dividing this cluster into smaller and smaller clusters. Linkage methods: Agglomerative methods of hierarchical clustering that cluster objects are based on computation of distances between them. Single linkage: Linkage method that is based on minimum distance or the nearest neighbor approach. Complete linkage: Linkage method that is based on maximum distance or the farthest neighbor approach. Average linkage: A Linkage method based on the average distance between all the pairs of objects, where one member of the pair is from each of the clusters. Select a clustering Procedure- Contd.. Variance methods: An agglomerative method of hierarchical clustering in which clusters are generated to minimize the within cluster variance. Ward’s procedure: variance method in which the squared Euclidean distance to the cluster means is minimized. Centroid methods: A Variance method of hierarchical clustering in which the distance between 2 clusters is the distance between their centroids. Select a clustering Procedure- Contd.. Non-hierarchical clusters: A Procedure that first assigns or determines a cluster center and then groups all objects within a prespecified threshold value from the center. Sequential threshold method: A non-hierarchical clustering method in which a cluster center is selected and all the objects within a prespecified threshold value from the center are grouped together. Parallel threshold method: Non-hierarchical clustering method that specifies several cluster centers at once. All objects that are within a prespecified threshold value from the center are grouped together. Optimizing partitioning method: Non-hierarchical clustering method that allows for later reassignment of objects to clusters to optimize an overall criterion. Cluster analysis is applicable An FMCG company wants to map the profile of its target audience in terms of lifestyle, attitude, and perceptions. A consumer durable company wants to know the features and services a consumer takes into account, when purchasing through catalogues. A housing finance corporation wants to identify and cluster the basic characteristics, lifestyles and mindset of persons who would be availing housing loans. Clustering can be done based on parameters such as interest rates, documentation, processing fee, number of installments Process There are 2 ways in which cluster analysis is carried out: First, objects/respondents are segmented into a pre- decided number of clusters. In this case a method called non-hierarchical method can be used which partitions data into the specified number of clusters. The second method is called the hierarchical method. Interpretation of Results Ideally the variables should be measured on an interval or ratio scale. This is because the clustering techniques use the distance measure to find the closest objects to group into clusters. An example of its use can be clustering of towns similar to each other which will help decide where to locate new retail stores. Interpretation of Results-Contd.. If clusters of customers are found based on their attitudes towards new products and interest in different kinds of activities an estimate of the segment size for each segment of the population can be obtained by looking at the number of objects in each cluster. Names can also be given to clusters to describe each one. Marketing strategies for each segment are based on segment characteristics. Steps in Cluster Analysis Selection of the sample to be clustered (buyers, products, employees) Definition on which the measurement to be made. (e.g. Product attributes, buyer behavior, characteristics) Clusters should be arranged in hierarchy. Cluster comparison and validation. Steps in Cluster Analysis-Contd.. Selection of the sample to be clustered (buyers, products, employees) Definition on which the measurement to be made. (e.g. product attributes, buyer characteristics). Computing the similarities among the entities. Arrange the clusters in hierarchy. Cluster comparison and validation. Conjoint Analysis A technique that attempts to determine the relative importance consumers attach salient attributes and the utilities they attach to the level of attributes. Conjoint analysis is concerned with the measurement of the joint effect of the 2 or more attributes that are important from the consumers point of view. Statistics associated with conjoint analysis Part worth functions: The part worth functions or utility functions describe the utility consumers attach to the levels of each attribute. Relative importance weights: The relative important weights are estimated and indicate which attributes are important in influencing consumer choice. Attribute levels: The attribute levels denote the values assumed by the attributes. Full profiles: Full profiles or complete profiles of brands are constructed in terms of all the attributes by using the attribute levels specified by the design. Pair wise tables: In Pair wise tables, the respondents evaluate two attributes at the same time until all the required pairs of attributes have been evaluated. Statistics associated with conjoint analysis-Contd.. Cyclical designs: Cyclical designs are designs employed to reduce the number of paired comparisons. Fractional factorial designs: Fractional factorial designs are designs employed to reduce the number of stimulus profiles to be evaluated in the full profile approach. Orthogonal arrays: Orthogonal arrays are a special class of factorial designs that enable the efficient estimation of all main effects. Internal validity: This involves correlations of the predicted evaluations for the holdout or validation stimuli with those obtained from the respondents. Steps in Conducting Conjoint Analysis Formulate the Problem Construct the Stimuli. Decide on the form of Input data. Select a Conjoint analysis procedure. Interpret the results. Assess reliability and validity. Conjoint Analysis Model Conjoint analysis model: The mathematical model expressing the fundamental relationship between attributes and utility in conjoint analysis. Conjoint Analysis Model-Contd.. The model estimated may be represented by: m ki U(X)= ∑ ∑ aij xij i=1 j=1 Where U(X)= overall utility of an alternative aij= the part worth contribution or associated with the jth level. (j, j= 1,2…..ki) of the ith attribute (i, i = 1,2……m) Ki = number of levels of attribute i m = number of attributes Xij = 1 if the jth level of ith attribute is present = 0 otherwise Hybrid Conjoint Analysis A form of conjoint analysis that can simplify the data collection task and estimate selected interactions as well as all its main effects. It has been developed to serve 2 main purposes: Simplify data collection task by imposing less burden on each respondent. Permit the estimation of selected interactions at the subgroup level as well as all main effects at individual level. Conjoint Analysis-Contd.. In a situation where the company would like to know the most desirable attributes or their combination for a new product or service, the use of conjoint analysis is not appropriate. Example for conjoint analysis An airline would like to know, which is the most desirable combination of attributes to a frequent traveller: Punctuality Airfare Quality of food served on the flight Hospitality and empathy shown Conjoint analysis.. Contd Conjoint analysis is a multivariate technique that captures the exact levels of utility that an individual consumer places on various attributes of the product offering. Conjoint analysis enables direct comparison. Example of conjoint analysis Designing an automobile loan or insurance plan in the insurance industry. Designing a complex machine for business customers. Process of conjoint analysis Design attributes for the product are first identified. For a shirt manufacturer, these could be design such as designer shirts Vs plain shirts, this price of Rs400 versus Rs.800. The outlets can have exclusive distribution. All possible combinations of these attributes level are then listed out. Each design combination will be ranked by customers and used as input data for conjoint analysis. Then the utility of the products relative to the price are measured. Process of conjoint analysis The output is a part-worth or utility for each level of each attribute. For example the design may get a utility level of 5 and plain as 7.5. Similarly, the exclusive distribution may have a part utility of 2, and mass distribution, 5.8. We then put together the part utilities and come up with a total utility for any product combination we want to offer and compare that with the maximum utility combination for this customer segment. Approach to conjoint analysis From a discussion with the client, identify the design attributes to be studied and the levels at which they can be offered. Then build a list of product concepts on offer. These product concepts are then ranked by customers. Once this data is available, use conjoint analysis to derive the part utilities of each attribute level. This is then used to predict the best product design for the given customer segment. Use the SPSS Conjoint procedure to analyse the data. Uses of Conjoint Analysis The uses of Conjoint analysis is as follows: Determining the relative importance of attributes in the consumer choice process. Estimating market share of brands that differ in attribute levels. Determining the composition of most preferred brand. Segmenting the market based on similarity of preferences for attribute levels. Applications of conjoint analysis have been made in consumer goods, industrial goods, financial and other services. MDS The most common and useful marketing application of multidimensional scaling is product positioning or brand positioning. Positioning is essentially concerned with mapping a consumers mind and placing all the competing brands of a product category in appropriate slots or positions on it. One obvious way to do that is to ask customers what they think of competing brands or say 6 attributes with a rating scale of 5 to 10 points. This would result in rating for all the brands on all attributes which could be taken as 2 attributes at a time and plotted on a graph. MDS A class of procedures for representing perceptions and preferences of respondents spatially by means of a virtual display. Perceived or psychological relationship among stimuli are represented as geometric relationships among points in a multidimensional space. Statistics and terms associated with MDS Similarity judgments: are ratings on all possible pairs of brands or other stimuli in terms of their similarity using a likert- type scale. Preference rankings: are rank ordering of the brands or other stimuli from the most preferred to least preferred . They are normally obtained from the respondents. Stress: This is lack of fit-measure; higher the values of stress indicates poor fits Statistics and terms associated with MDS- Contd.. R-Square: R Square is a squared correlation Index that indicates the proportion of variance of the optimally scaled data that can be accounted for by the MDS Procedure. This is a goodness of fit measure. Spatial map: Perceived relationship among brands or other stimuli are represented as geometric relationship among points in a Multi Dimensional space called spatial map. Coordinates: indicate the positioning of a brand or a stimulus in a spatial map. unfolding: The representation of both brands and respondents as points in the same space is referred to as unfolding. Conducting MDS Formulate the problem Obtain input data Select an MDS Procedure Decide on the number of dimensions. Label the dimensions and interpret the configuration. Assess reliability and validity. Conducting MDS-Contd.. Obtain Input Data: Perception Data: Direct Approaches: In Direct Approaches to gathering perception data, the respondent, the respondents are asked to judge how similar or dissimilar the various brands or stimuli are, using their own criteria. Respondents are often required to rate all possible pairs of brands or stimuli in terms of similarity on a likert scale. These data are referred to as similarity judgements. Example Similarity judgments on all the possible pairs of toothpaste brands may be obtained in the following manner: very very Dissimilar similar Colgate vs. Crest 1 2 3 4 5 6 7 Aqua fresh vs,crest 1 2 3 4 5 6 7 Colgate vs aquafresh 1 2 3 4 5 6 7 The number of pairs to be evaluated is n(n-1)/2, where n is the number of stimuli. Other procedures are also available. Conducting MDS- Contd.. Derived approach: In MDS attribute based approach to collecting perception data requiring the respondents to rate the stimuli on the identified attributes using semantic differential or likert scale For example different brands of toothpaste may be rated on attributes such as: Whitens ------------------------------------------Does not teeth whiten teeth Conducting MDS- Contd.. Direct Vs Derived Approach: Direct approaches have the advantage that the researcher does not have to identify a set of salient attributes. Respondents make similarity judgments using their own criteria, as they would under normal circumstances. The disadvantages are that the criteria are influenced by the brands or stimuli being evaluated. If various brands of automobiles being evaluated are in the same price range, then price will not emerge as an important factor. It may be difficult to determine before analysis if and how the individual respondents judgment should be combined. Conducting MDS- Contd.. Direct Vs Derived Approach: The advantage of Derived or Attribute based approach is that it is easy to identify respondents with homogenous perceptions. The respondents can be clustered based on the attribute ratings. It is also easier to label the dimensions. A disadvantage is that the researcher must identify all the salient attributes a difficult task. The spatial map obtained depends on the attributes identified. Conducting MDS- Contd.. Select an MDS Procedure Non-metric MDS- A type of MDS method that assumes that the input data are ordinal. Metric MDS- A MDS method that assumes that the input data are metric. Conducting MDS- Contd.. Decide on Number of Dimensions: The following guidelines are suggested for determining the number of dimensions: A priori knowledge: theory or past research may suggest a particular number of dimensions. Interpretability of the spatial map: Generally it is difficult to interpret configurations or maps derived in more than 3 dimensions. Elbow criterion: A plot of stress versus dimensionality should be examined. The point in this plot usually form a convex pattern. The point at which a n elbow or a sharp bend occurs indicates appropriate no of dimensions. Ease of use: it is generally easier to work with 2 dimensional maps or configurations than with those involving more dimensions. Statistical approach: It is used for determining dimensionality. Conducting MDS- Contd.. Scaling Preference Data: Internal Preference Data: Takes into account both brands stimuli and respondent points. External analysis of preference: vectors based on preference data. Example of MDS A product category of shampoos could be identified as having 5 attributes important to consumers- price, lather, fragrance, consistency, and favorable effects on hair. If this were to be rated on a 7-point scale for say six leading brands of shampoo A, B, C,D,E, and F, then we could pick up any 2 attributes and plot the six brands on a map according to consumer ratings. Example of MDS- Contd.. For example if we plotted rating on price Versus rating on favorable effect on hair, we may find that all the 6 brands are positioned in different places based on consumer ratings or perceptions. This is called perceptual map of consumer perception about competing brands in a product category. Methods of MDS Attribute based approach Similarity/dissimilarity based approach Recommended Usage Knowing particular attribute Number of dimensions as well as interpretation. Naming of attributes of the brands and their target segment such as age, price, quality, or attempted positioning through brand communication and so on. Research report There are 2 types of report Oral report Written report Oral report: This type of reporting is required, when the researchers are asked to make an oral presentation. Making an oral presentation is somewhat difficult compared to written report. This is because the reporter has to interact directly with the audience. Any faltering during an oral presentation can leave a negative impression on the audience. Nature of an oral presentation Opening Finding/Conclusion Recommendation Method of presentation. Points to remember in oral presentation Language used must be simple and understandable. Time Management should be adhered. Use of charts, graphs etc, will enhance understanding by the audience. Vital data such as figures, may be printed and circulated to the audience, so that their ability to comprehend increases. The presenter should know his target audience well in advance. The presenter should know the purpose of the report. Guidelines for oral report Employ visual aids Avoid reading the report KYA- Know Your Audience Plan and deliver. Types of written reports On the basis of time interval reports can be classified as: Daily, Weekly, Monthly, Quarterly, Yearly Types of Report: Short Report, long Report, Formal Report, Informal Report, Government Report. Preparation of written reports Preparation of research report: The following is the format of research report: Title Page Page contents/Table of contents Executive Summary Introduction Methodology Data collection and Analysis Conclusions Suggestions and Recommendations Bibliography. Appendix Explanation of contents of reports Executive summary: This includes a brief detail of what the report consists of. It should be written in one or two pages. Body: this section include: Introduction: the introduction should clearly explain the decision problem. Sometimes it consists of details about the topic, company profile etc. Contents of report- contd.. Methodology: this includes the following: Statement of objectives Data collection method: whether primary, secondary data or both. Questionnaire design, ie tools for data collection. Sample design: which includes sample type, sample size etc. Contents of report- contd.. Analysis and interpretation: this should include analysis of question in the questionnaire by using tables and graphs and other statistical tools. Contents of report- contd.. Conclusions: this includes the conclusions drawn from the study. Suggestions and recommendations: based on the conclusions, suggestions and recommendations are made. Appendix: the purpose of appendix is to provide a place for material which is not absolutely necessary in the body of the report: such as questionnaire, broucher etc. Bibliography If portions of the report is based on secondary data, use bibliography section to list the publications or sources that you have consulted. It includes: Title of the book Name of the journal in case of article Volume no Page number Edition Writing the Report- Contd.. Pre writing considerations: The outline : Major Topic Heading A Major subtopic heading 1. Sub topic a. Minor subtopic (1) Further details (a) Even further details I. Writing the Report- Contd.. Writing Considerations: Contd.. The Bibliography Writing the Draft Readability Comprehensibility Tone Final proof. Presenting the research report Carrying out professional approach Use short paragraphs Use headings and subheadings Use vertical listings of points. Incident part of the text that represents listings, long quotations or examples. Presenting the research report Presentation of statistics involves 4 ways: A text paragraph Semi tabular form Tables Graphics Pie charts Presenting the research report Preparation Opening Findings and conclusions Recommendations. Delivery Presenting the research report- Contd.. Common Research Problems Speaker problems Vocal characteristics: Should not speak too softly Do not speak to rapidly Vary volume tone quality Do not use overworked pet phrase, uhs, etc. Do not stare into space Do not misuse visuals Do not hitch or tug on clothing, scratch or fiddle with pocket. Do not rock back and forth or twist from side to side, or lean too much on the lectern. Presenting the research report- Contd.. Other problems Cost considerations Limitations on time Quality of research report Effectiveness of research. Presenting the research report Audio-Visuals Low tech: Chalk board and white boards Hand out materials Flip charts Overhead transparencies. Slides High Tech Computer drawn visuals Computer animations Writing the research Report- Contd.. Other guidelines: Consider the audience Attitude 1: adopt fresh mind approach Kiss Approach (Keep it short and simple). Oral and written report Distinguish between oral and written report: oral Report No rigid standard format Remembering all that is said is difficult if not impossible. This is because the presenter cannot be interrupted frequently for clarification. Tone, voice modulation, comprehensibility and several other communication factors play an important role. Correcting mistakes if any is difficult. The audience has no control over the speed of presentation. The audience does not have the choice of picking and choosing from the presentation. Oral and written report Distinguish between oral and written report: Written Report Standard format can be adopted This can be read a number of times and clarification can be sought whenever the reader chooses. Free from presentation problems. Mistakes if any, can be pinpointed and corrected. Not applicable The reader can pick and choose what he thinks is relevant to him. For instance, the need for information is different for technical and non technical persons.