Like this presentation? Why not share!

Scaling techniques.ppt

by Narayanan Palani www.NarayananP.com, Team Lead at Lloyds TSB on Mar 25, 2012

• 22,148 views

Views

Total Views
22,148
Views on SlideShare
22,148
Embed Views
0

Likes
3
857
1

No embeds

Categories

Uploaded via SlideShare as Microsoft PowerPoint

Report content

11 of 1 previous next

• Consider an attitude scale from 1 to 100. Each respondent is assigned a number from 1 to 100, with 1 = Extremely Unfavorable, and 100 = Extremely Favorable. Measurement is the actual assignment of a number from 1 to 100 to each respondent. Scaling is the process of placing the respondents on a continuum with respect to their attitude towards department stores.
• * The numbers serve only as labels or tags for identifying and classifying objects. * When used for identification, there is a strict one-to-one correspondence between the numbers and the objects. * The numbers do not reflect the amount of the characteristic possessed by the objects. * The only permissible operation on the numbers in a nominal scale is counting. * Only a limited number of statistics, all of which are based on frequency counts, are permissible, e.g., percentages, and mode.
• A ranking scale in which numbers are assigned to objects to indicate the relative extent to which the objects possess some characteristic. Can determine whether an object has more or less of a characteristic than some other object, but not how much more or less. Any series of numbers can be assigned that preserves the ordered relationships between the objects. In addition to the counting operation allowable for nominal scale data, ordinal scales permit the use of statistics based on centiles, e.g., percentile, quartile, median.
• Numerically equal distances on the scale represent equal values in the characteristic being measured. It permits comparison of the differences between objects. The location of the zero point is not fixed. Both the zero point and the units of measurement are arbitrary. Any positive linear transformation of the form y = a + bx will preserve the properties of the scale. It is not meaningful to take ratios of scale values. Statistical techniques that may be used include all of those that can be applied to nominal and ordinal data, and in addition the arithmetic mean, standard deviation, and other statistics commonly used in marketing research.
• Possesses all the properties of the nominal, ordinal, and interval scales.It has an absolute zero point. It is meaningful to compute ratios of scale values. Only proportionate transformations of the form y = bx, where b is a positive constant, are allowed. All statistical techniques can be applied to ratio data.
• 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.Tend to reduce halo or carryover effects from one judgment to another.
• 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.Tend to reduce halo or carryover effects from one judgment to another.

Scaling techniques.pptPresentation Transcript

• K. J. Somaiya Institute of Management Studies & ResearchMeasurement & Scaling  Haresh - 001  Palani - 009  Raman VG - 017  Keyur - 011 Measurement, Scaling, Questionnaire & 1 Form Design
• Measurement & Scaling  Fundamentals & Comparitive Scaling  Non-Comparitive Scaling Techniques  Questionnaire & Form Design Measurement, Scaling, Questionnaire & 2 Form Design
• Measurement & Scaling Outline: 1) Overview 2) Measurement and Scaling 3) Scales Characteristics Description, Order, Distance, Origin 4) Primary Scales of Measurement Nominal, Ordinal, Interval, Ratio 5) A Comparison of Scaling Techniques Measurement, Scaling, Questionnaire & 3 Form Design
• Measurement & Scaling Outline: *Contd…+6) Comparative Scaling Techniques i. Paired Comparison ii. Rank Order Scaling iii. Constant Sum Scaling iv. Q-Sort and Other Procedures Measurement, Scaling, Questionnaire & 4 Form Design
• Measurement & Scaling Measurement: Is nothing but assigning numbers / other symbols to characteristics of objects according to pre-specified rules Rules should:  Standardized  Uniformly applied  Not change over time Measurement, Scaling, Questionnaire & 5 Form Design
• Measurement & ScalingScales CharacteristicsDescription The unique labels / descriptors used to designate each value of the scaleOrder The relative sizes / positions of the descriptors. Denoted as < = or >Distance Absolute differences between descriptors expressed in units.Origin The scale has a unique or fixed beginning / true zero point. Measurement, Scaling, Questionnaire & 6 Form Design
• Measurement & ScalingScaling involves creating a continuum uponwhich measured objects are located. Attitude Scale 1 = Extremely Unfavorable 2 3 . . .100 = Extremely FavorableMeasurement  Actual assignment of a NumbersScaling  The process of placing the respondents on continuum Measurement, Scaling, Questionnaire & 7 Form Design
• Measurement & Scaling Primary Scales of MeasurementNominal Numbers Finish Assigned 7 8 3Ordinal Rank Order of Winners Finish Third Second First place place placeInterval Performance Rating on a 8.2 9.1 9.6 0 to 10 ScaleRatio Time to Finish 15.2 14.1 13.4 in Seconds Measurement, Scaling, Questionnaire & 8 Form Design
• Measurement & Scaling Primary Scales of Measurement Nominal Scale• serve as Tags for identifying objects.• One-to-one correspondence• Do not reflect the amount of the characteristic• Counting is the only permissible operation• Limited number of statistics based on frequency counts• e.g. percentages and mode Measurement, Scaling, Questionnaire & 9 Form Design
• Measurement & Scaling Illustration of Primary Scales of Measurement Interval Nominal Ordinal Scale Ratio Scale Scale Preference Scale Preference Ratings \$ spent last No. Store Rankings 1-7 11-17 3 months 1. Parisian 7 79 5 15 0 2. Macy’s 2 25 7 17 200 3. Kmart 8 82 4 14 0 4. Kohl’s 3 30 6 16 100 5. J.C. Penney 1 10 7 17 250 6. Neiman Marcus 5 53 5 15 35 7. Marshalls 9 95 4 14 0 8. Saks Fifth Avenue 6 61 5 15 100 9. Sears 4 45 6 16 0 10.Wal-Mart 10 115 2 12 10 Measurement, Scaling, Questionnaire & 10 Form Design
• Measurement & Scaling Primary Scales of MeasurementOrdinal Scale• Relative extent to which the objects possess some characteristic.• Can determine whether an object has more or less of a characteristic than some other object• Numbers that preserves the ordered relationships between the objects can be assigned• permit the use of statistics based on centiles, e.g., percentile, quartile, median. Measurement, Scaling, Questionnaire & 11 Form Design
• Measurement & Scaling Primary Scales of MeasurementInterval Scale• Equal distances represent equal values• Permits comparison of differences between objects.• The location of the zero point is not fixed.• Positive linear transformation of the form y = a + bx will preserve properties• Taking ratios of scale values is not meaningful• All commonly used in marketing research statistical techniques may be used. Measurement, Scaling, Questionnaire & 12 Form Design
• Measurement & Scaling Primary Scales of MeasurementRatio Scale• Possesses all the properties of the nominal, ordinal, and interval scales• Has an absolute zero point• Meaningful to compute ratios of scale values• Only proportionate transformations of the form y = bx, where b is a positive constant, are allowed• All statistical techniques can be applied Measurement, Scaling, Questionnaire & 13 Form Design
• Measurement & Scaling Primary Scales of Measurement Relative Advantages• Small differences between stimulus objects• Same known reference points for all respondents• Easy to understand and apply• Fewer theoretical assumptions• Tend to reduce halo or carryover effects Measurement, Scaling, Questionnaire & 14 Form Design
• Measurement & Scaling Primary Scales of Measurement Limitations• Ordinal nature of the data• Inability to generalize beyond stimulus objects scaled. Measurement, Scaling, Questionnaire & 15 Form Design
• Measurement and Scaling:Noncomparative Scaling Techniques Measurement, Scaling, Questionnaire & 16 Form Design
• • Respondents evaluate only one object at a time, and for this reason noncomparative scales are often referred to as monadic scales.• Noncomparative techniques consist of continuous and itemized rating scales. Measurement, Scaling, Questionnaire & 17 Form Design
• Classification Noncomparative Rating Scales Continuous ItemizedRating Scales Rating Scales Semantic Stapel Likert Differential Measurement, Scaling, Questionnaire & 18 Form Design
• Continuous Rating ScaleRespondents 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.The form of the continuous scale may vary considerably.How would you rate Sears as a department store?Version 1Probably the worst - - - - - - -I - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Probably the bestVersion 2Probably the worst - - - - - - -I - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -- - Probably the best0 10 20 30 40 50 60 70 80 90 100Version 3 Very bad Neither good Very good nor badProbably the worst - - - - - - -I - - - - - - - - - - - - - - - - - - - - - -- - - - - - - - - - - - - - - - -Probably the best0 10 20 30 40 50 60 70 80 90 100 Measurement, Scaling, Questionnaire & 19 Form Design 19
• Itemized Rating Scales• The respondents are provided with a scale that has a number or brief description associated with each category.• The categories are ordered in terms of scale position, and the respondents are required to select the specified category that best describes the object being rated.• The commonly used itemized rating scales are the Likert, semantic differential, and Stapel scales. Using the 5-point scale provided, pleaseAre you satisfied with our indicate how satisfy you are with ourservice? service Measurement, Scaling, Questionnaire & 20 Form Design
• Itemized Rating Scales: (1) Likert Scale / Summated-Ratings ScaleThe Likert scale requires the respondents to indicate a degree of agreement ordisagreement with each of a series of statements about the stimulus objects. Strongly Disagree Neither Agree Strongly disagree agree nor agree Reversed score: disagree (5+1)-2 = 41. M&S sells high quality merchandise. 1 2 3 4 52. M&S has poor in-store service. 1 2 3 4 53. I like to shop at M&S. 1 2 3 4 5• The analysis can be conducted on an item-by-item basis (profile analysis), or a total (summated) score can be calculated.• When arriving at a total score, the categories assigned to the negative statements by the respondents should be scored by reversing the scale. Measurement, Scaling, Questionnaire & 21 Form Design 21
• Itemized Rating Scales: (2) Semantic Differential ScaleThe semantic differential is a seven-point rating scale with endpoints associated with bipolar labels that have semantic meaning. Marks & Spencer 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.• This controls the tendency of some respondents, particularly those with very positive or very negative attitudes, to mark the right- or left-hand sides without reading the labels.• Individual items on a semantic differential scale may be scored on either a -3 to +3 or a 1 to 7 scale. Measurement, Scaling, Questionnaire & 22 Form Design 22
• Itemized Rating Scales: (3) Stapel ScaleThe Stapel scale is a unipolar rating scale with ten categoriesnumbered from -5 to +5, without a neutral point (zero). Thisscale is usually presented vertically. +5 +5 +5 +4 +4 +4 +3 +3 +3 +2 +2X +2 +1 +1 +1HIGH QUALITY POOR SERVICE WIDE VARIETY -1 -1 -1 -2 -2 -2 -3 -3 -3 -4X -4 -4 -5 -5 -5The data obtained by using a Stapel scale can be analyzed in the same way as semantic differential data. Measurement, Scaling, Questionnaire & 23 Form Design
• Table 10.1 Basic Noncomparative ScalesScale Basic Characteristics Examples Advantages DisadvantagesContinuous Place a mark on a Reaction to TV Easy to Scoring can beRating continuous line commercials construct cumbersomeScale unless computerizedItemizedRating ScalesLikert Scale Degree of agreement Measurement of Easy to More time on a 1 (strongly attitudes construct, consuming disagree) to 5 (strongly administer, and agree) scale understandSemantic Seven-point scale with Brand, product, Versatile Difficult to cons-Differential bipolar labels and company truct bipolar images adjectivesStapel Unipolar ten-point scale, Measurement of Easy to Confusing andScale -5 to +5, without a attitudes and construct and difficult to apply neutral point (zero) images administer over telephone Measurement, Scaling, Questionnaire & 24 Form Design 24
• Figure 10.4 Balanced and Unbalanced Scales Balanced Scale Unbalanced Scale Surfing the Internet is Surfing the Internet is____ Extremely Good ____ Extremely Good____ Very Good ____ Very Good____ Good ____ Good____ Bad ____ Somewhat Good____ Very Bad ____ Bad____ Extremely Bad ____ Very Bad Measurement, Scaling, Questionnaire & 25 Form Design
• Figure 10.5 Rating Scale ConfigurationsA variety of scale configurations may be employed to measure the comfort of Nikeshoes. Some examples include:Nike shoes are:1) Place an “X” on one of the blank spaces…Very VeryUncomfortable Comfortable2) Circle the number…Very 1 2 3 4 5 6 7 VeryUncomfortable Comfortable3) Place an “X” on one of the blank spaces… Very Uncomfortable Uncomfortable Neither Uncomfortable nor Comfortable Comfortable Measurement, Scaling, Questionnaire & Very Comfortable Form Design 26 26
• Some Unique Rating Scale ConfigurationsThermometer ScaleInstructions: Please indicate how much you like McDonald’s hamburgersby coloring in the thermometer. Start at the bottom and color up to thetemperature level that best indicates how strong your preference is. Like veryForm: much - 100 75 - 50 - 25 Dislike very 0 muchSmiling Face ScaleInstructions: Please point to the face that shows how much you like theBarbie Doll. If you do not like the Barbie Doll at all, you would point to Face1. If you liked it very much, you would point to Face 5.Form: Measurement, Scaling, Questionnaire & 1 2 Form Design 3 4 5 27 27
• Developing a Multi-Item Scale Develop the Construct Develop a Theoretical Definition Develop an Operational Definition Develop a Multi-Item Scale•Generate a Pool of Scale Items•Reduce the Pool of Items•Based on Judgment•Collect Data•Purify the Scale Based on Statistical Analysis Evaluate Scale Reliability and Validity Apply the Scale and Accumulate Research Findings Measurement, Scaling, Questionnaire & 28 Form Design
• Scale Evaluation Scale Evaluation Validity Reliability ContentTest-Retest Internal Criterion Consistency Alternative Forms Construct Convergent Validity Discriminant Validity Nomological Validity Measurement, Scaling, Questionnaire & 29 Form Design
• Questionnaire and Form Design Measurement, Scaling, Questionnaire & 30 Form Design
• Questionnaire• A formalized set of questions for obtaining information from respondents.• Objective of Questionnaire – Translate information needed into specific questions – Questionnaire should uplift, motivate, and encourage the respondent to involve and complete interview – It must minimize response error. Measurement, Scaling, Questionnaire & 31 Form Design
• Questionnaire Design Specify the Information Needed Specify the Type of Interviewing Method Determine the Content of Individual QuestionsDesign the Question to Overcome the Respondent’s Inability and Unwillingness to Answer Decide the Question Structure Determine the Question Wording Arrange the Questions in Proper Order Identify the Form and Layout Reproduce the Questionnaire Eliminate Bugs by Pre-testing Measurement, Scaling, Questionnaire & 32 Form Design
• Questionnaire Design (Cont’d)• Specify Information needed – It is the first step for questionnaire design as it helps in clearly understanding needs• Type of Interviewing method – Mail Questionnaire – Telephone Questionnaire – Personal Questionnaire – Electronic Questionnaire (very similar to mail questionnaire) Measurement, Scaling, Questionnaire & 33 Form Design
• Questionnaire Design (Cont’d)• Individual Question Content – Is the question necessary? – Are several questions needed instead of one?• E.g.:-“Do you think Coca-Cola is a tasty and refreshingsoft drink??”“Do you think Coca-Cola is a tasty soft drink?”“Do you think Coca-Cola is a refreshing softdrink?” Measurement, Scaling, Questionnaire & 34 Form Design
• Questionnaire Design (Cont’d)• Overcoming inability to answer – Is the Respondent informed? e.g.:- A husband may not be aware of monthly expenses for groceries and department store if wife make purchase or vice versa – Can the Respondent Remember? – Can the Respondent articulate? e.g.:- If asked to describe the atmosphere of the department store. Measurement, Scaling, Questionnaire & 35 Form Design
• Questionnaire Design (Cont’d)• Overcome Unwillingness to Answer – Effort required of the Respondents – Context – Legitimate Purpose – Sensitive information – Increase the willingness of Respondents• Choosing Question Structure – Unstructured Question – Structured Question Measurement, Scaling, Questionnaire & 36 Form Design
• Choosing Question Wording• define the issue• use ordinary words• use unambiguous words• avoid leading questions• avoid implicit alternatives• avoid implicit assumptions• avoid generalizations and estimates• use positive and negative statements
• Define the issueThe Ws Defining the QuestionWho The Respondent It is not clear whether this question relates to the individual respondent or the respondents total household.What The Brand of Shampoo It is unclear how the respondent is to answer this question if more than one brand is used.When Unclear The time frame is not specified in this question. The respondent could interpret it as meaning the shampoo used this morning, this week, or over the past year.Where At home, at the gym, on the road?
• Define the issue A question should clearly define the issue being addressed• Which brand of shampoo do you use??• Which brand or brands of shampoo have you personally used at home during the last month? In case of more than one brand, please list all the brands that apply?
• Use ordinary Wordsordinary words should be used in questionnaire vocabulary level should match the respondents vocabulary• Do you think the distribution of soft drink is adequate??• Do you think soft drinks are readily available when you want them to buy?
• Use Unambiguous WordsWords in questionnaire should have a single meaning known to respondents• In a typical month how often do you shop in department store??Never….. Occassional ….. Sometimes…..Often….. Regularly…..• In a typical month how often do you shop in department store?Less than once….. 1 or 2 times…. 3 or 4 times….More than 4 times…..
• Avoid leading questionsA leading question clues, the respondent toanswer in a certain way• Do you think patriotic Americans should buy imported automobiles when that would put American labor out of work??• Do you think Americans should buy imported automobile?
• Avoid implicit alternativesAlternative not explicitly expressed is an implicit alternative• Do you like to fly when travelling short distances??• Do you like to fly when travelling short distances or would you rather drive?
• Avoid implicit assumptionsQuestions should not be worded so that the answer is dependent upon implicit assumption• Are you in favor of a balanced budget??• Are you in favor of a balanced budget if it would result in an increase in the personal income tax?
• Avoid Generalizations and Estimates• Questions should be specific not general• Respondent does not make generalization or compute science• What is the annual per capita expenditure on groceries in your household??• What is the monthly expenditure on groceries in your household and How many members are their in your household?
• Determining the order of questionsOpening question• Can be crucial in gaining the confidence, should be interesting, simple, and non threateningType of Information• As a general guideline, basic information should be obtained first, followed by classification, and, finally, identification informationDifficult Questions• Difficult questions which are sensitive, embarrassing, complex, or dull, should be placed late in the sequence
• Funnel Approach• Questions asked in sequence can influence the response to subsequent question• So questions asked from general to specific• What considerations are important to you in selecting a department store??• In selecting a department store how important is convenience or location?
• Form and Layout• format, spacing and positioning questions have significant effect on results• should be numbered serially• 2000 population of census reveals questions at the top received more importance than the bottom• Instructions in red made little difference that they made the questionnaire appear more complicated
• Reproduction of Questionnaire• Paper quality can reflect on project• Vertical response columns• Tendency to crowd should be avoided• Instructions to be placed close to the question• Motto easy to read and answer• Should be large and clear
• PretestingTesting of the questionnaire on a sample toidentify and eliminate potential errors• General rule• Respondents similar to the actual survey• Variety of interviewers used• All aspects of the questionnaire should be tested• Protocol analysis (think aloud) & debriefing are two used procedures
• Q&AMeasurement, Scaling, Questionnaire & 51 Form Design