Attitude Measurement

Marketing ResearchAaker, Kumar, Leone and Day Twelfth EditionInstructor’s Presentation Slides1Chapter Eleven2Attitude MeasurementMarketing Research 12th Edition Attitude MeasurementUsed to understand and influence behavior since: 3Concept exists that attitudes lead to behaviorMore feasible to ask questions on attitudes than to observe and interpret behaviorCapacity for diagnosis and explanationLearn which features of a new product concept are acceptable or unacceptableMeasure the perceived strengths and weaknesses of competitive alternativesMarketing Research 12th Edition What Are Attitudes?Mental states used by individuals to structure the way they perceive their environment and guide the way they respond to itComponents of attitude:Cognitive or Knowledge componentAffective or Liking componentIntention or Action component4Marketing Research 12th Edition Cognitive or Knowledge Component5A person’s information about an objectAwareness of existence of the objectBeliefs about the characteristics or attributes of the objectJudgments about the relative importance of each of the attributesMarketing Research 12th Edition Affective or Liking ComponentSummarizes a person’s overall feelings toward an object, situation, or person on a scale of like-dislike or favorable-unfavorableWhen there are several alternatives, liking is expressed in terms of preference for one alternativePreference measured by asking which alternative is “most preferred” or “first choice,” which is the “second choice,” and so on6Marketing Research 12th Edition Intention or Action ComponentRefers to a person’s expectations of future behavior toward an objectIntentions are usually limited to a distinct time period that depends on buying habits and planning horizons Incorporates information about a respondent’s ability or willingness to pay for the object, or otherwise take action7Marketing Research 12th Edition Concept of MeasurementMeasurement is a standardized process of assigning numbers or other symbols to certain characteristics of objects of interest, according to pre-specified rulesCharacteristics for standardization of measurementOne-to-one correspondence between the symbol and the characteristic in the object that is being measuredRules for assignment should be invariant over time and the objects being measured8Marketing Research 12th Edition ScalingProcess of creating a continuum on which objects are located according to the amount of the measured characteristic possessedTypes of measurement scale:9NominalOrdinalIntervalRatioMarketing Research 12th Edition Nominal Scale10Are you a resident of Connecticut? Yes No Are you 1) Caucasian 2) African-American 3) Hispanic 4) Asian 5) OtherObjects are assigned to mutually exclusive, labeled categoriesNo necessary relationships among categoriesNo ordering or spacing are impliedOnly possible arithmetic operation is a count of each categoryMarketing Research 12th Edition Ordinal or Rank Scale11Rank your preferences for the following attributes in making a car purchase decisionPrice -----------Safety -----------Design -----------Fuel economy ------------Ranks objects or arranges them in order by some common variableDoes not provide information on how much difference there is between objectsArithmetic operations are limited to statistics such as median or modeMarketing Research 12th Edition Interval Scale12On a scale of 1 to 7, how would you rate the performance of natural gas as home heating fuel in terms of reliability of supply? (1 being least reliable and 7 being most reliable)1 2 3 4 5 6 7Numbers used to rank objects also represent equal increments of the attribute being measured Differences can be comparedEntire range of statistical operations can be employed for analysisMarketing Research 12th Edition Ratio Scale13How old are you? _________What is your zip code?______Type of interval scale with meaningful zero point Possible to say how many times greater or smaller one object is than anotherOnly scale that permits comparisons of absolute magnitudeMarketing Research 12th Edition Types of Scales and Their Properties14Marketing Research 12th Edition Attitude Rating ScalesPresent a respondent with a continuum of numbered categories that represent the range of possible attitude adjustmentsClassified as:Single item scalesMultiple item scales15Marketing Research 12th Edition 16Marketing Research 12th Edition Classification of Attitude ScalesSingle Item ScalesOnly have one item to measure a construct Types of Single item scales 17Itemized-categoryComparativeRank-orderQ-sortPictoralConstant sumPaired-ComparisonMarketing Research 12th Edition Itemized-category ScalesRespondent selects from a limited number of categories 18________ Very Satisfied_________ Quite Satisfied_________ Somewhat Satisfied_________ Not at all Satisfied`Marketing Research 12th Edition Comparative ScaleA judgment comparing one object, concept, or person against one another19Marketing Research 12th Edition Rank-order ScalesRespondent compares one item with another or a group of items against each other and ranks them20Marketing Research 12th Edition Q-sort ScalingRespondents sort comparative characteristics into normally distributed groupsTen or more groups increases accuracy of results 21Marketing Research 12th Edition Constant-sum ScaleRespondents allocate a fixed number of rating points among serial objects to reflect relative preference22Marketing Research 12th Edition Pictorial ScalesVarious categories of the scale are depicted pictoriallyThermometer ScaleFunny faces scaleFormat must be comprehensible to respond and allow accurate response23Like very muchDislike very much10075 50 25 0Marketing Research 12th Edition The brands to be rated are presented two at a time, so each brand in the category is compared once to every other brandBrands are rated on a given number of points that are then divided between the two brands on the basis of respondents’ preferences Frame of reference is always the other brand being tested; these brands may change over time24CompareA and BA and CA and DB and CB and DC and DMarketing Research 12th Edition Paired – Comparison ScalesIssues in Designing Single-Item Scales25BalancedVery good ______Good ______Bad ______Very Bad ______UnbalancedSuperb ______Very Good ______Good ______Average ______Types of poles used in the scaleNumber of scale categoriesStrength of the anchorsBalance of the scaleLabeling of the categoriesMarketing Research 12th Edition For eg: Smell of Morning Dew isMultiple-item ScalesDeveloped to measure a sample of beliefs toward the attitude objects and combine the set of answers into an average score Types of multiple-item scales:26Likert ScaleThurstone ScalesSemantic-Differential ScalesMarketing Research 12th Edition Likert ScaleRequires respondent to indicate degree of agreement or disagreement with a variety of statements related to the attitude objectAlso called Summated Scale since scores on individual items are summed to give total score for respondentsUsually consists of item part and evaluative partLikert scale is unidimensional27Marketing Research 12th Edition Likert Scale – Example28Marketing Research 12th Edition Thurstone ScalesAlso known as the method of equal-appearing intervals since objective is to obtain a unidimensional scale with interval properties29Step 1: Generate a large number of statements or adjectives reflecting all degrees of favorableness toward the attitude objectsStep 2: A group of judges is given this set of items and asked to classify them according to their degree of favorableness or unfavorableness Marketing Research 12th Edition Thurstone Scales (contd.)30AdvantagesEasy to administerRequires minimum instructionsLimitationsTime consumingExpensive to constructNot as much diagnostic value as a Likert scaleValues depend on the attitudes of the original judgesMarketing Research 12th Edition Semantic-Differential ScaleRespondents rate each attribute object on a number of five or seven-point rating scales bounded by polar adjectives or phrasesWith bipolar scale, the midpoint is a neutral point31Marketing Research 12th Edition Semantic-Differential Scale (contd.)Pairs of objects or phrases selected must be meaningful in market being studied and correspond to product/service attributesRotate negative pole on either side to avoid "halo" effect Category increments are treated as interval scales so group mean values can be computed for each object on each scaleMay also be analyzed as a summated rating scale32Marketing Research 12th Edition Profile AnalysisApplication of semantic differential scalePlot mean ratings for each object on each scale for visual comparisonOverall comparison of brands hard to grasp with many brands and attributesNot all attributes are independent33Marketing Research 12th Edition Stapel ScalesUses one pole rather than two opposite polesRespondents select a numerical response categoryHigh positive score reflects good fit between adjective and objectEasy to administer and constructNo need to assure bipolarity34Marketing Research 12th Edition Associative ScalingMost effective for markets where respondent is knowledgeable only about a small subset of a large number of choicesAppropriate to choice situations that involve a sequential decision processBest suited to market tracking where the emphasis is on understanding shifts in relative competitive positions35Marketing Research 12th Edition General Guidelines For Developing A Multiple-Item Scale36Determine clearly what you are going to measureGenerate as many items as possibleAsk experts in the field to evaluate the initial pool of itemsDetermine the type of attitudinal scale to be usedInclude some items that will help in the validation of the scaleEvaluate and refine the itemsAdminister the items to an initial sampleFinally, optimize the scale lengthMarketing Research 12th Edition Choosing An Attitudinal Scale37Problems in choosing a scaleDifferent techniques with different strengths and weaknessesVirtually any technique can be adapted to the measurement of any one of the attitude componentsResearchers’ choice shaped byThe specific information requiredAdaptability of the scale to the data collection method and budget constraintsCompatibility of the scale with the structure of the respondent’s attitudeMarketing Research 12th Edition Accuracy of Attitude MeasurementsValidity: An attitude measure has validity if it measures what it is supposed to measure38Face or Consensus Validity The extent to which the content of a measurement scale appears to tap all relevant facets of the constructCriterion ValidityBased on empirical evidence that the attitude measure correlates with other “criterion” variablesConcurrent ValidityTwo variables are measured at the same timePredictive ValidityThe attitude measure can predict some future eventMarketing Research 12th Edition Accuracy of Attitude Measurements (Cont.)39Convergent ValidityA form of construct validity that represents the association between the measured construct and measures of other constructs with which the construct is related on theoretical groundsDiscriminant ValidityA form of construct validity that represents the extent to which the measured construct is not associated with which the construct is related on theoretical groundsConstruct ValidityA scale evaluation criterion that relates to the underlying question "what is the nature of the underlying variable or construct measured by the scale?"Marketing Research 12th Edition Accuracy of Attitude Measurements (Contd.)40ReliabilityThe consistency with which the measure produces the same results with the same or comparable populationSensitivityExtent to which ratings provided by a scale are able to discriminate between the respondents who differ with respect to the construct being measuredGeneralizabilityRefers to the ease of scale administration and interpretation in different research settings and situationsRelevancyRelevance = reliability * validityMarketing Research 12th Edition Scales in Cross-National ResearchResponses Can Be Affected by:Low literacy and educational levelsCulture; semantic differential scale is closest to pan-cultural scaleAdapting response formats, particularly their calibration, for specific countries and cultures41Marketing Research 12th Edition 42End of Chapter Eleven