You are on page 1of 85

DATA COLLECTION; MEASUREMENT & SCALING TECHNIQUES

MODULE 4

DATA COLLECTION
DATA Means Facts, information or premises, systematically collected and formally presented for the purpose of drawing inferences Collection : data collection is the process of obtaining valuable and reliable information for purpose of research

Primary Data:
• The data directly collected by the researcher, with respect to the problem under study , is known as primary data. Primary data is also the first-hand data collected by the researcher for the immediate purpose of the study Secondary data Secondary data are statistics that already exit , They have been gathered not for immediate use. This may be described as “those data that have been compiled by some agency other than the user”.

Internal sources of secondary data Secondary data can be obtained internally i e within the firm
Internal sources of secondary data

Accounting Records

Internal Experts

Sales force reports

Misce reports

Govt Publication – Central statistical organization (CSO) – National Accounting Statistic – Basic Statistics Relating to the Indian Economy – Reserve Bank of India Bulletin – Currency and Finance Report .• External sources of secondary Data 1.

Special collection 8.Books and Periodicals 3.Non-govt Associations Indian cotton mills Federation publisher statistics on the cotton textile industry The American Statistics Index etc 4. Internet 9. Directories Yellow pages 5.Database format . Industry Experts 7.2.

Reports abased on the marketing information collected by such organizations are sent periodically ( weekly. monthly. syndicated services may be regarded as an “intermediate” source falling between the primary and secondary sources .SYNDICATED DATA Syndicated services are provided by certain organizations. or quarterly) to clients who are subscribers. which collect and tabulate marketing information on a continuing basis.

weekly. quarterly. or annually Panel surveys those surveys that are conducted among a group of respondents who have agreed to respond to a number of mail. monthly.Syndicated data can be collected using the following • Surveys: –Periodic surveys –Panel surveys –Shared survey Periodic surveys: theses are surveys that are conducted at regular intervals. telephone and personal interviews over a period of time .

. Hence.• Shared surveys • Shared surveys conducted by a research firm use questionnaires that contain a pool of questions which are of interest to different clients. these are known as multi-clients surveys ands are sometimes called omnibus surveys.

thus saving them lot of money and time € Secondary data can help identify . and takes less time to gather.€ Secondary data is used by managers as it is cheaper. clarity and redefine the research problem € secondary data might also hold a solution to the problem € Secondary data may provide alternatives methods that can be used for primary research € Secondary data generates requisite information for better creativity Advantages of secondary data .

Disadvantages of secondary data • • • • Lack of availability Lack of relevance Inaccurate data Insufficient data .

Observation : – Information is collected by observing the process at work – Difficulties in observation » Inadequacies of our sense organs » Interdependence of observation and inference » Effects of interaction between the observer and the observed .Modes of data collection 1.

scope and objectives of the study  Observation is always purposeful  It captures the natural social context in which person’s behavior occurs . It is a physical and mental activity Characteristics of observations  It is selective. The research selects the range of things to be observed on the basis of nature.

• Methods of observation • Structured –unstructured observation – Structured observation is used when the research problem has been formulated precisely and the observers have been told specifically what is to be observed. They may be given a simple form to record their observations – Unstructured observation : observers are free to observe whatever they think is relevant and important .

the respondents do not know that they are being observed In non-disguised observation. the respondents are well aware that they are being observed Ex.Disguised.undisguised observation In disguised observation.Indirect observation In direct observation. Indirect observation implies that some record of past behaviour is observed . observers often pose as shoppers Direct. the event or the behaviour of a person is observed as it occurs.

enables the observer to control extraneous variables which influence the behaviour of people. on the other hand .Observation under natural settinglaboratory setting Observation in a laboratory setting. .

such information can be obtained by the researcher through observation ex . especially when the observed person are unaware of their behavior being observed Advantages of observation method .small children  it is easier to conduct disguised observation studies than disguised questioning  There is no element of artificialness in observational studies. The original data can be collected at the time of occurrence of the event  Observation is done in natural surroundings.  Sometimes.. the respondents may not like to part with some of the information.

Disadvantages of observation • The observer might wait for longer period at the point of observation • extensive training of observers is required • This is an expensive method • It is very difficult to gather information on (1) opinions (2) intentions .

DESIGNING THE QUESTIONNAIRE Questionnaire is a tool used to collect the data .

. to cooperate. motivate. • A questionnaire must uplift.Questionnaire Objectives • It must translate the information needed into a set of specific questions that the respondents can and will answer. and encourage the respondent to become involved in the interview. • A questionnaire should minimize response error. and to complete the interview.

Can the respondent answer the question accurately? •4 what is the chance of the responses being influenced by external events? •5. what is the utility of the data collected? 2. Is the respondent willing to answer the question accurately? . How effective is a question in producing the required data? 3.•Question content •Researcher has to find answers to 5 major questions while deciding the question content they are 1.

to facilitate analysis and interpretation • It must keep the respondent interested throughout . so as to allow the interviewer to keep the interview to the point • It should be well arranged.Characteristics of questionnaire • It must be simple. the respondents should be able to understand the questions • It must generate relies that can be easily be recorded by the interviewer • It should be specific .

a) The utility of data b) Effectiveness in producing data c) The participant’s Ability to Answer Accurately d) The Respondent’s willingness to answer accurately e) Effect of external events .

Principles for preparing a questionnaire  A short letter is enclosed  Enclose a self addressed stamped envelop for the respondent’s convenience in returning the questionnaire  Assure the respondent that his answers will be kept in confidence  promise the respondent that he will not be solicited after he fills up the questionnaire  if possible. offer special inducements ( free gifts) to return the questionnaire  If the respondent is interested . promise a copy of the results of the survey to him .

Participants to respond in his /her own words without being restricted to pre-defined response choices is known as an open-ended question • What do you think of the performance of the Indian hockey team in the recent Olympics? • Which brand of soft drink do you like ? Coke or Pepsi? . open-ended questions.Types of questions • 1.

age ..g. Advantage a) eliminates "forced choice" bias b) unlimited response varieties Disadvantage a) promotes investigator bias b) responses difficult to code and analyze Best Use a) small scale exploration b) establishing rapport c) as final question d) to collect facts: e.1) OPEN-ENDED QUESTIONS: Respondents are given complete freedom to answer in their own words.

These questions have the response options “yes” or “No” or “True” or “ False” Agree or Disagree .Binary These are also known as dichotomous questions as they permit only two possible answers. The respondent has to choose one of the two permissible answers .Close-ended questions 1.

CLOSED-ENDED QUESTIONS: A) Yes – No Questions: Respondents are limited to a positive or negative position. Advantage a) minimizes investigator bias b) responses obtained quickly c) coding is simple and inexpensive Disadvantage a) Best Use simplistic / limits range of commitment b) wording can cause biases a) telephone interview b) self-administered questionnaire when topic permits .

. • Competitive pricing.......... • Instant home delivery ……………………... • Recommended by a friends or relative …………….......... . • Regular discounts offered …………………..• Ranking questions • These questions require the participant to rank the response options listed on a continuum basis in order of preference • Ranking questions are used to get information that reveals participants attitudes and opinions • The factors that influence your decision to buy from a particular supermarket are listed below please rank them from the most important (1) to the least important ( 7) • Conveniently located ………………. • Helpful sales staff ………………..... • Availability of everything I need…………………..

Excellent Very Good 5 4 Average 3 Fair 2 Poor 1 .

Multiple-choice question These questions cover all significant degrees of response. the respondent has to select an option that best describes their feelings. Advantage a) minimizes investigator bias b) responses obtained quickly c) coding is simple and inexpensive d) permits greater range of commitment than yes-no questions Disadvantage a) good questions are difficult to write b) wording can cause biases Best Use a) personal interview b) self-administered questionnaire c) telephone interview if item is not too complicated . These are mostly a variation of binary questions Multiple Choice Questions: Respondents are limited to choice of more than two positions.

Checklist questions These are questions where the participant has the freedom to choose one or more of the response options available Q. Which premium brand of shirts do you possess? ( tick as many of the following as apply) Allen Solly Louise Phillippe Van Heusen Color Plus Zodiac .

Process construction of questionnaire Information sought Type of questionnaire to be used Writing a first draft Re-examining and revising questions Pre-testing and editing the questionnaire Specifying procedure for its use .

Wording Use correct grammar and sentence structure. . Wording should be neutral and clearly communicate the intent of question. Avoid slang and colloquialisms. Wording should be as simple as possible without being condescending to respondent. Consider the measurement scale and statistical analysis to be used. Use a conversational tone.Questionnaire Design Preliminary Concerns Consider the data collection method. Wording should be as closely as possible to the manner in which people would talk to each other.

Making interview .Types of Interview • Interview – Structured/ formal interview – Unstructured interview – Stress interview – Group interview method – Panel interview – In.depth interview – Decision.

because different questions are asked according to the respondents attitude and participation  The findings emerge in a form which is fully understandable to the clients . closer.Merits of interview  The interview method of data collection is often fast and cheap  This method brings the respondent who supplies information and client who use it.  This method is quite flexible.

Demerits of interview
• It does not indicate how extensive the attitudes expressed by the participants are: • The data is not at all projectable • This method of data collection cannot cover large areas • Mush of the results depend on the moderator

• Scales of measurement Criteria for good measurement: measurement • 1.Reliability Reliable measuring scales provide stable measures at different times under different conditions. Ex; coffees vending machine gives the same quality of coffee every time then it can be concluded that the measurement of the coffee vending machine is reliable .

2.Validity The ability of a scale or a measuring instrument to measure what it is intended to measure can be termed as the validity of the measurement . 3. Objectivity 4. Simplicity 5. Accuracy 6. Economy

Measurement and Scaling
Measurement means assigning numbers or other symbols to characteristics of objects according to certain pre-specified rules.

One-to-one correspondence between the numbers and the characteristics being measured. The rules for assigning numbers should be standardized and applied uniformly. Rules must not change over objects or time.

less than. we mean the unique labels or descriptors that are used to designate each value of the scale. and equal to. . Order By order. we mean the relative sizes or positions of the descriptors.Scale Characteristics Description By description. Order is denoted by descriptors such as greater than. All scales possess description.

Scale Characteristics Distance The characteristic of distance means that absolute differences between the scale descriptors are known and may be expressed in units. Origin The origin characteristic means that the scale has a unique or fixed beginning or true zero point. .

with 1 = Extremely Unfavorable. Each respondent is assigned a number from 1 to 100. Measurement is the actual assignment of a number from 1 to 100 to each respondent. .Measurement and Scaling Scaling involves creating a continuum upon which measured objects are located. and 100 = Extremely Favorable. Consider an attitude scale from 1 to 100. Scaling is the process of placing the respondents on a continuum with respect to their attitude toward department stores.

6 Finish Interval Performance Rating on a 0 to 10 Scale Time to Finish in Seconds Ratio 15.1 First place 9.1 13.2 14.Scale Nominal Primary Scales of Measurement Numbers Assigned to Runners Finish 7 8 3 Ordinal Rank Order of Winners Third place 8.2 Second place 9.4 .

regression Ratio Length. standard deviation Product-moment correlation. weight Age. sales. zero point is arbitrary Zero point is fixed. store types Permissible Statistics Descriptive Inferential Percentages. binomial test Nominal Numbers identify & Social Security nos. classify objects numbering of football players Ordinal Nos. Range.Primary Scales of Measurement Scale Basic Characteristics Common Examples Marketing Examples Brand nos. Preference relative positions of rankings of teams in a rankings. indicate the Quality rankings. ratios of scale values can be compared Temperature (Fahrenheit) Celsius) Percentile. mode Chi-square. opinions. Friedman ANOVA Interval Attitudes. market objects but not the tournament position. costs Geometric mean. income.. index nos. harmonic mean Coefficient of variation . mean. median Rank-order correlation. t tests.. social magnitude of class differences between them Differences between objects can be compared.

A Classification of Scaling Techniques Scaling Techniques Comparative Scales Noncomparative Scales Paired Comparison Rank Order Constant Sum Q-Sort and Other Procedures Continuous Rating Itemized Rating Scales Scales Likert Semantic Differential Stapel .

. • In noncomparative scales. Comparative scale data must be interpreted in relative terms and have only ordinal or rank order properties. The resulting data are generally assumed to be interval or ratio scaled. each object is scaled independently of the others in the stimulus set.A Comparison of Scaling Techniques • Comparative scales involve the direct comparison of stimulus objects.

• Tend to reduce halo or carryover effects from one judgment to another.Relative Advantages of Comparative Scales • Small differences between stimulus objects can be detected. • Same known reference points for all respondents. • Easily understood and can be applied. . • Involve fewer theoretical assumptions.

please indicate which one of the two brands of shampoo you would prefer for personal use. Recording Form: Jhirmack Finesse Vidal Sassoon Head & Shoulders Pert a Jhirmack Finess Vidal Head & Pert e Sassoo Shoulders n 0 0 1 0 1a 1 0 1 1 0 1 0 0 0 1 1 1 0 1 0 Number of 3 2 0 4 1 A 1 in a particular box means that the brand in that column was preferred over the brand in the corresponding row. A 0 means that the row brand was preferred over the column brand.Obtaining Shampoo Preferences Using Paired Comparisons Instructions: We are going to present you with ten pairs of shampoo brands. For each pair. bThe number of times a brand was preferred is obtained by summing the 1s in each column. .

but its introduction was less than successful.Paired Comparison Selling The most common method of taste testing is paired comparison. self-perception and brand reputation are very important factors in the consumer’s purchasing decision. because image plays a major role in the purchase of Coke.000 responses is considered an adequate sample. The test is done in private and a minimum of 1. A paired comparison taste test . where imagery. A blind taste test for a soft drink. New Coke was heavily favored in blind paired comparison taste tests. may not be a good indicator of performance in the marketplace. The consumer is asked to sample two different products and select the one with the most appealing taste. The introduction of New Coke illustrates this point.

1) scaling decisions need be made in rank order scaling. • Furthermore. • Only (n . . rank order scaling also results in ordinal data.Comparative Scaling Techniques Rank Order Scaling • Respondents are presented with several objects simultaneously and asked to order or rank them according to some criterion. • It is possible that the respondent may dislike the brand ranked 1 in an absolute sense.

Preference for Toothpaste Brands Using Rank Order Scaling Instructions: Rank the various brands of toothpaste in order of preference. No two brands should receive the same rank number. The criterion of preference is entirely up to you. The least preferred brand should be assigned a rank of 10. There is no right or wrong answer. Continue this procedure until you have ranked all the brands of toothpaste in order of preference. Then find the second most preferred brand and assign it a number 2. . Begin by picking out the one brand that you like most and assign it a number 1. Just try to be consistent.

Crest 2. Pepsodent 9. Aim 4. Sensodyne 6. Close Up 8. Ultra Brite 7. Colgate 3. Gleem 5.Preference for Toothpaste Brands Using Rank Order Scaling Form Brand 1. Plus White 10. Stripe Rank Order _________ _________ _________ _________ _________ _________ _________ _________ _________ _________ .

Comparative Scaling Techniques Constant Sum Scaling • Respondents allocate a constant sum of units. Hence. such as 100 points to attributes of a product to reflect their importance. . the respondent assigns it zero points. the name of the scale. • If an attribute is twice as important as some other attribute. • The sum of all the points is 100. • If an attribute is unimportant. it receives twice as many points.

If an attribute is not at all important. there are eight attributes of bathing soaps. The more points an attribute receives. Please allocate 100 points among the attributes so that your allocation reflects the relative importance you attach to each attribute. assign it zero points. the more important the attribute is. . If an attribute is twice as important as some other attribute.Importance of Bathing Soap Attributes Using a Constant Sum Scale Instructions On the next slide. it should receive twice as many points.

Price 5. Lather 3. Cleaning Power Sum Segment I 8 2 3 53 9 7 5 13 100 Segment II 2 4 9 17 0 5 3 60 100 Segment III 4 17 7 9 19 9 20 15 100 . Packaging 7. Moisturizing 8. Mildness 2. Fragrance 6. Shrinkage 4.Importance of Bathing Soap Attributes Using a Constant Sum Scale Form Average Responses of Three Segments Attribute 1.

. • Non-comparative techniques consist of continuous and itemized rating scales.Non comparative Scaling Techniques • Respondents evaluate only one object at a time. and for this reason non-comparative scales are often referred to as monadic scales.

..---Probably the best 0 10 20 30 40 50 60 70 80 90 100 Very bad ........................ How would you rate Sears as a department store? Version 1 Probably the worst ........--Probably the best 0 10 20 30 40 50 60 70 80 90 100 Version 3 Neither good Very good nor bad Probably the worst ................ The form of the continuous scale may vary considerably........-I ....Continuous Rating Scale Respondents rate the objects by placing a mark at the appropriate position on a line that runs from one extreme of the criterion variable to the other...Probably the best Version 2 Probably the worst ..-I ...............-I ..

The responses are also stored in a permanent data file for use in further analysis. the perception analyzer.Perception Analyzer A relatively new research tool.” A group of up to 400 respondents is presented with TV or radio spots or advertising copy. income. The measuring device consists of a dial that contains a 100-point range. The response scores can be broken down by categories. the information is fed to a computer. As the respondents turn the dials. sex. provides continuous measurement of “gut reaction. enabling the researcher to view the respondents' scores immediately. . Each participant is given a dial and instructed to continuously record his or her reaction to the material being tested. which tabulates second-by-second response profiles. such as age. As the results are recorded by the computer. or product usage. they are superimposed on a video screen.

• The commonly used itemized rating scales are the Likert. • The categories are ordered in terms of scale position.Itemized Rating Scales • The respondents are provided with a scale that has a number or brief description associated with each category. and Stapel scales. and the respondents are required to select the specified category that best describes the object being rated. . semantic differential.

the categories assigned to the negative statements by the respondents should be scored by reversing the scale. 2. or a total (summated) score can be calculated. Big-Bazzar sells high-quality merchandise. Strongly Disagree Neither Agree disagree agree nor agree disagree 1. 3. I like to shop at Big-Bazzar 1 1 1 2X 2 2X 3 3X 3 4 4 4 5 5 5 Strongly • The analysis can be conducted on an item-by-item basis (profile analysis). • When arriving at a total score. Big-Bazzar has poor in-store service. .Likert Scale The Likert scale requires the respondents to indicate a degree of agreement or disagreement with each of a series of statements about the stimulus objects.

5=strongly agree  Big bazzar Sells high quality merchandise (2) Big bazzar has a poor instore service (2) I like to shop at big bazzar (3) Big bazzar do not offer a good mix of different brands within a product category(4) The credit policies at big bazzar is terrible (3) I do not like the advertising done by the big bazzar (3) Big bazzar sells a wide variety of merchandise (4) Big bazzar is the best place to shop (4)        .Pls indicate how strong you agree or disagree with each by using the following scale: 1=strongly disagree.2=disagree.Example of Likert Scale Listed below are different opinion about Big-Bazzar .4=agree.3=neither agree nor disagree.

This controls the tendency of some respondents. Individual items on a semantic differential scale may be scored on either a -3 to +3 or a 1 to 7 scale.Semantic Differential Scale The semantic differential is a seven-point rating scale with end points associated with bipolar labels that have semantic meaning.or left-hand sides without reading the labels. • • . particularly those with very positive or very negative attitudes. to mark the right. Big-Bazzar is : Powerful --:--:--:--:-X-:--:--: Weak Unreliable • --:--:--:--:--:-X-:--: Reliable Modern --:--:--:--:--:--:-X-: Old-fashioned The negative adjective or phrase sometimes appears at the left side of the scale and sometimes at the right.

Person Concepts. and Product Concepts 1) Rugged 2) Excitable 3) Uncomfortable 4) Dominating 5) Thrifty 6) Pleasant 7) Contemporary 8) Organized 9) Rational 10) Youthful 11) Formal 12) Orthodox 13) Complex 14) Colorless 15) Modest :---:---:---:---:---:---:---: Delicate :---:---:---:---:---:---:---: Calm :---:---:---:---:---:---:---: Comfortable :---:---:---:---:---:---:---: Submissive :---:---:---:---:---:---:---: Indulgent :---:---:---:---:---:---:---: Unpleasant :---:---:---:---:---:---:---: Obsolete :---:---:---:---:---:---:---: Unorganized :---:---:---:---:---:---:---: Emotional :---:---:---:---:---:---:---: Mature :---:---:---:---:---:---:---: Informal :---:---:---:---:---:---:---: Liberal :---:---:---:---:---:---:---: Simple :---:---:---:---:---:---:---: Colorful :---:---:---:---:---:---:---: Vain .A Semantic Differential Scale for Measuring SelfConcepts.

SEARS +5 +4 +3 +2 +1 HIGH QUALITY -1 -2 -3 -4X -5 +5 +4 +3 +2X +1 POOR SERVICE -1 -2 -3 -4 -5 The data obtained by using a Stapel scale can be analyzed in the same way as semantic differential data. . without a neutral point (zero).Stapel Scale The Stapel scale is a unipolar rating scale with ten categories numbered from -5 to +5. This scale is usually presented vertically.

administer.point scale. and understand More time . . product.Basic Noncomparative Scales Scale Continuous Rating Scale Basic Characteristics Place a mark on a continuous line Examples Reaction to TV commercials Advantages Easy to construct Disadvantages Scoring can be cumbersome unless computerized Itemized Rating Scales Likert Scale Degrees of agreement on a 1 (strongly disagree) to 5 (strongly agree) scale Seven .point scale with bipolar labels Measurement of attitudes Easy to construct.consuming Semantic Differential Brand. without a neutral point (zero) Easy to construct.5 to +5. and company images Measurement of attitudes and images Versatile Controversy as to whether the data are interval Stapel Scale Unipolar ten . administer over telephone Confusing and difficult to apply .

optimal number. the accuracy of the data may be improved by a non-forced scale 5) Verbal description An argument can be made for labeling all or many scale categories. The category descriptions should be located as close to the response categories as possible A number of options should be tried and the best selected 6) Physical form . of categories If a neutral or indifferent scale response is possible for at least some respondents. unbalanced In general. an odd number of categories should be used 4) Forced vs. non-forced In situations where the respondents are expected to have no opinion.Summary of Itemized Scale Decisions 1) Number of categories Although there is no single. the scale should be balanced to obtain objective data 3) Odd/even no. traditional guidelines suggest that there should be between five and nine categories 2) Balanced vs.

Balanced and Unbalanced Scales Jovan Musk for Men is: Extremely good Very good Good Bad Very bad Extremely bad Jovan Musk for Men is: Extremely good Very good Good Somewhat good Bad Very bad .

Very gentle 4) ____ ____ ____ ____ ____ Very Harsh Somewhat Neither harsh Somewhat harsh harsh nor gentle gentle ____ ____ Gentle Very gentle -3 •5) Very harsh -2 -1 Neither harsh nor gentle 0 +1 Very +2 gentle +3 .Rating Scale Configurations Tide detergent is: 1) Very harsh 2) Very harsh --1 ----2 3 --4 --5 --6 --7 Very gentle Very gentle 3) . Very harsh . . Tide . . Neither harsh nor gentle . .

you would point to Face 1. If you liked it very much. you would point to Face 5. If you do not like the Barbie Doll at all. Start at the bottom and color up to the temperature level that best indicates how strong your preference is. . Like very much Dislike very much 100 75 50 25 0 Smiling Face Scale Instructions: Please point to the face that shows how much you like the Barbie Doll.Some Unique Rating Scale Configurations Thermometer Scale Instructions: Please indicate how much you like McDonald’s hamburgers by coloring in the thermometer.

Nor Probably Satisfied Will Buy Might or Might Not Buy Sometimes Often .Some Commonly Used Scales in Marketing CONSTRUCT SCALE DESCRIPTORS Attitude Importance Satisfaction Purchase Intent Purchase Freq Very Bad Not at All Important Very Dissatisfied Bad Not Important Dissatisfied Neither Bad Nor Good Neutral Good Important Satisfied Very Good Very Important Very Satisfied Definitely Will Buy Very Often Probably Will Definitely will Not Not Buy Buy Never Rarely Neither Dissat.

 . The axes of the spatial map are assumed to denote the psychological bases or underlying dimensions respondents use to form perceptions and preferences for stimuli.  These geometric representations are often called spatial maps.Multidimensional Scaling (MDS) Multidimensional scaling (MDS) is a class of procedures for representing perceptions and preferences of respondents spatially by means of a visual display.  Perceived or psychological relationships among stimuli are represented as geometric relationships among points in a multidimensional space.

Conducting Multidimensional Scaling Specify the purpose for which the MDS results would be used. theory.  The choice of the number and specific brands or stimuli to be included should be based on the statement of the marketing research problem. and the judgment of the researcher.  Select the brands or other stimuli to be included in the analysis.  . The number of brands or stimuli selected normally varies between 8 and 25.

Input Data for Multidimensional Scaling MDS Input Data Perceptions Preferences Direct (Similarity Judgments) Derived (Attribute Ratings) .

Crest 1 23 Crest vs. . Aim 1 23 4 5 . These data are referred to as similarity judgments. . . In direct approaches to gathering perception data. Colgate vs. Colgate 1 23 4 Aqua-Fresh vs. using their own criteria. the respondents are asked to judge how similar or dissimilar the various brands or stimuli are. where n is the number of stimuli. Very Dissimilar Crest vs.Conducting Multidimensional Scaling Obtain Input Data Perception Data: Direct Approaches. Aqua-Fresh 1 23 Very Similar 5 6 7 4 5 6 7 6 7 4 5 6 7 The number of pairs to be evaluated is n (n -1)/2.

Similarity Rating Of Toothpaste Brands Aqua-Fresh Aqua-Fresh Crest Colgate Aim Gleem Macleans Ultra Brite Close-Up 5 6 4 2 3 2 2 Crest Colgate Aim Gleem Macleans Ultra Brite Close-Up Pepsodent 7 6 3 3 2 2 6 4 4 2 2 5 4 3 2 5 5 6 5 5 6 .

whiten teeth Whitens Does not teeth ___ ___ ___ ___ ___ ___ ___ ___ ___ ___ Prevents tooth Does not prevent decay ___ ___ ___ ___ ___ ___ ___ ___ ___ ___ tooth decay . Pleasant Unpleasant tasting ___ ___ ___ ___ ___ ___ ___ ___ ___ ___ tasting  If attribute ratings are obtained. Derived approaches to collecting perception data are attribute-based approaches requiring the respondents to rate the brands or stimuli on the identified attributes using semantic differential or Likert scales. .Conducting Multidimensional Scaling Obtain Input Data  Perception Data: Derived Approaches. a similarity measure (such as Euclidean distance) is derived for each pair of brands. . . .

5 2.0 .5 Dentagard Macleans Ultrabrite Pepsodent Colgate Close Up Aqua.Fresh Gleem Aim Crest -1.A Spatial Map of Toothpaste Brands 2.5 0.0 -0.5 -2.0 -0.5 1.5 1.0 -1.0 -2.0 1.0 0.5 0.0 1.0 -1.0 0.5 -1.

0 0.0 1.0 -0.5 1.0 0.5 2.5 0.0 1.0 -1.5 0.5 -1.0 .5 -1.Using Attribute Vectors to Label Dimensions 2.0 -2.Fresh Gleem Aim Crest Fights Cavities Cleans Stains -2.5 1.0 -0.5 Whitens Teeth Dentagard Macleans Ultrabrite Pepsodent Close Up Colgate Aqua.0 -1.

Can be used to model nonlinear relationships. gives insight into how individuals differ from aggregate data.“Advantages” of MDS      Does not require assumptions of linearity. Reveals dimensions without the need for defined attributes. or multivariate normality. Dimensionality “solution” can be obtained from individuals. Dimensions that emerge from MDS can be incorporated into regression analysis to assess their relationship with other variables. . metricity.

MDS assumes that the distance (similarity) between two stimuli is some function of their partial similarities on each of several perceptual dimensions. A limitation of MDS is that dimension interpretation relating physical changes in brands or stimuli to changes in the perceptual map is difficult at best.Assumptions and Limitations of MDS It is assumed that the similarity of stimulus A to B is the same as the similarity of stimulus B to A. . When a spatial map is obtained. it is assumed that inter-point distances are ratio scaled and that the axes of the map are multidimensional interval scaled.

Thurstone scale Thurstone scale was the first formal technique for measuring an attitude. and a mean score is computed. It is made up of statements about a particular issue. It was developed by Louis Leon Thurstone in 1928. People check each of the statements to which they agree. . as a means of measuring attitudes towards religion. and each statement has a numerical value indicating how favorable or unfavorable it is judged to be. indicating their attitude.

Thurstone scale In an attempt to approximate an interval level of measurement. It also can accommodate neutral statements. psychologist Robert Thurstone developed the method of equal-appearing intervals. . for developing an attitude scale compensates for the limitation of the Likert scale in that the strength of the individual items is taken into account in computing the attitude score. This technique.

2. 6.Thurstone Equal-appearing interval Scale 1. Get a set of judges to rate the statements in terms of how much they agree with them. The difference between these is the interquartile range. 4. For each statement. Choose the one with the lowest interquartile range for each position. from 1 (agree least) to 11 (agree most). Select a set of statements that are equal positions across the range of medians. 5. Sort the list by median value (This is the 'common' score in terms of agreement). Generate a large set of possible statements. plot a histogram of the numbers against which the different judges scored it. identify the median score. 3. the number below 25% (Q1) and below 75% (Q3). For each statement. .