Designing the Questionnaire

Marketing ResearchAaker, Kumar, Leone and Day Twelfth EditionInstructor’s Presentation Slides1Chapter TwelveDesigning the Questionnaire2Marketing Research 12th Edition Designing the QuestionnaireQuestionnaire building is an art!3A questionnaireis always custom-built!Marketing Research 12th Edition FORMATTING THE QUESTIONNAIREIn each issue, determine the content of each question.Decide on the format of each questionThe Process of Questionnaire Design4PLANNING WHAT TO MEASURERevisit the research objectivesDecide on the research issue of your questionnaireGet additional information on the research issue from secondary data sources and exploratory researchDecide on what is to be asked under the research issueDecide how you want to analyze the data collected.Marketing Research 12th Edition The Process of Questionnaire Design (Contd.)5SEQUENCING AND LAYOUT DECISIONSLay out the questions in a proper sequenceGroup all the questions in each subtopic to get a single questionnairePRETESTING AND CORRECTING PROBLEMSRead through the whole questionnaire to check whether it makes sense and it measures what it is supposed to measureCheck the questionnaire for errorPretest the questionnaireCorrect the problemsMarketing Research 12th Edition QUESTION WORDINGDetermine how the question is wordedEvaluate each research question on the basis of comprehensibility, knowledge and ability, willingness/inclination of a typical respondent to answer the questionDesigning the Questionnaire6Planning What to MeasureSpecify research objectives and information to be collected Determine relevance and scope of the studyPretest preliminary versions of the questionnaireTranslating Research Objectives Into Information RequirementsQuestions should address hypotheses to be testedMarketing Research 12th Edition Designing the Questionnaire (Contd.) Formatting the Question Decide on the degree of freedom to be given to the respondents in answering the questions 7Alternatives Open ended with no classification Open ended where the interviewer uses pre-coded classifications to record the response Close ended or structured format in which a question or a supplementary card presents the responses to be consideredMarketing Research 12th Edition Open-Response QuestionsFor introduction to a survey or to a topicWhen it is important to measure the salience of an issue to a respondentWhen there are too many responses to be listed, or they cannot be foreseenWhen verbatim responses are desired to give the flavor of people's answers or to cite examplesWhen the behavior to be measured is sensitive or disapproved8How do you feel about the public transportation in downtown Hartford?--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------Marketing Research 12th Edition Open Response Questions (Contd.)9AdvantagesWide range of responsesResponses obtained without any influenceFree choicesDisadvantagesVariability in the clarity and depth of the responses depends onArticulateness of the respondent in personal interviewWillingness to compose a written answer for a mail surveyInterviewer's ability to record the verbatim answers quicklyInterviewer bias while recording response Time consumingInvolves subjective judgments during summarization and are prone to errorExpensiveAnswers expand or contract depending on the space or time availableRespondents may not use the same frame of reference when the options are not availableMarketing Research 12th Edition Closed Response QuestionsTwo Basic Formats for Closed Ended or Structured Questions:10Choice from a list of responsesAppropriate single-choice rating on a scaleMarketing Research 12th Edition Closed Response Questions (Contd.) 11AdvantagesEasier to answerRequire less effort by the interviewerTabulation and analysis is easierLess potential error in the way the question is asked and the way it is recordedThe responses are directly comparable from respondent to respondentLimitationsDisagreement among researchers on the type of responses to be listedThe answer to a closed response question will be received no matter how relevant or irrelevant the question is in that contextMay not produce meaningful resultsDichotomous questions are prone to a large amount of measurement error because the alternatives are polarizedProvides fewer opportunities of self expressionAlternative responses provides answers not considered by the respondent, leading to selection of a "reasonable" responseMarketing Research 12th Edition Designing The Questionnaire (contd.)Number of Response Categories Generally five to seven categoriesIdeally the multiple choices should be mutually exclusiveOrder of Response Categories : Can affect responsesWhat factor influences your fast-food restaurant choice most ? Convenient location  Quality of food Menu selection  Fast service  Reasonable prices  Brand name CleanlinessTo prevent order bias, place the average or expected response at various positions in the sequence of categories12Marketing Research 12th Edition Range of Response CategoriesRespondents who do not know the answer might take categories as cues.13How many long-distance calls do you make in a week? less than 5  less than 10 5-10 or  10-20 More than 10.  More than 20.Marketing Research 12th Edition Handling Uncertainty and Ignorance Concerns the handling of “don’t know” and neutral responsesMay be advisable to provide the interviewer with an additional “no answer” category to identify these people correctly14Marketing Research 12th Edition Using Both Open-Response & Closed-Response QuestionsProbe: Using an open-response question to follow up a closed-response questionTwo general purposes for the use of probes:Pinpoint questions that were particularly difficult for respondentsAid researcher interpretation of respondent answers15Marketing Research 12th Edition Question Wording16Is the vocabulary simple, direct, and familiar to all respondents?Do any words have vague or ambiguous meanings?Are any questions " double-barreled”?Are any questions leading or loaded?Are the instructions potentially confusing?Is the question applicable to all respondents?Are the questions of appropriate length?Marketing Research 12th Edition Question Wording (contd.)Avoid ambiguous words How many times per month do you visit a fast-food restaurant?NeverOccasionallySometimesOftenCheck if any of the questions are loadedDon’t you think, because it’s so greasy, fast-food is one of the worst types of food? Do you prefer a hamburger that is grilled on a hot stainless-steel grill or cooked by passing the raw meat through an open gas flame?17Marketing Research 12th Edition Question Wording (contd.)Are any questions "double-barreled”? Are you satisfied with the price and the service of Taco Bell?Is the question applicable to all respondents? Why do you like fast-food? Assumes that respondent likes fast-food!18Marketing Research 12th Edition Asking Sensitive Questions Example: Consumption of Kellogg’s Frosted FlakesThe casual approach “Have you eaten ‘Frosted Flakes’ within the last week?The numbered card “Would you please read off the number on this card that corresponds to what you had eaten for breakfast in the last week?” (Hand card to respondent)PancakesFrosted FlakesOther (what)?19Marketing Research 12th Edition Asking Sensitive Questions (Cont.)The everybody approach“As you know, many people have been eating Frosted Flakes for breakfast.Do you eat Frosted Flakes?”The “other people” approach“Do you know of any adult who eats Frosted Flakes?”“How about yourself?”20Marketing Research 12th Edition Asking Sensitive Questions (Contd.)The sealed ballot techniqueExplain that the survey respects people’s right to anonymity with respect to their eating habits andRespondents themselves are to fill out the answer to the question, seal it in an envelope, and drop it in a box conspicuously labeled “sealed ballet box” carried by the interviewerThe Kinsey approachLook into respondent’s eyes and ask in simple clear-cut language “Do you eat Frosted Flakes for breakfast?”21Marketing Research 12th Edition Asking Sensitive Questions (Contd.)Randomized Response TechniqueThe respondent is asked to answer one or two randomly selected questions without revealing which question has been answeredQuestions:SensitiveInnocuous Since the interviewer records a “yes” or “no” answer without knowing which question has been answered, the respondent feels free to answer honestly22Marketing Research 12th Edition Randomized Response TechniqueP[Yes] = P[Yes|S.Q] * P[S.Q] + P[Yes|I.Q] * P[I.Q]whereS.Q = Sensitive QuestionI.Q = Innocent Question23Marketing Research 12th Edition Sequence And Layout DecisionsOpen with an easy and non-threatening questionEnsure that questionnaire has smooth and logical flow from one topic to the nextProceed from broad general questions to more specific onesDo not place sensitive or difficult questions dealing with income status, ability etc at the beginning of the questionnaireUse good quality of paperMake physical layout appealing and interesting24Marketing Research 12th Edition Organization of a Typical Questionnaire25Marketing Research 12th Edition Order Bias: Does The Question Create The Answer?26 Marketing Research 12th Edition Pretest DesignPretesting Specific Questions For:Pretesting the Questionnaire to:Test flow of the questionnaire for clarity and logic Ensure that skip patterns are clear and well laid out Time each section so that questionnaire does not appear very long Capture and maintain respondent interest and attention27VariationMeaningTask DifficultyRespondent Interest and AttentionMarketing Research 12th Edition Considerations in Questionnaire Design for International ResearchOpen-ended questions avoid the imposition of cultural bias by the researcher since they do not impose any structure or response categories. If the topic is perceived as sensitive by the respondent, it is better to use an indirect format than a direct one.Where research is conducted in countries or cultures with high levels of illiteracy, it is often desirable to use nonverbal stimuli such as show cards. The wording of questions has to be changed according to the country in which the questionnaire is being administered since categories, such as income, education, occupation, or the dwelling unit, are not always exactly comparable from one culture or country to another.The most significant problems in drawing up questions in multi-country research are likely to occur in relation to attitudinal, psychographic, and lifestyle data.28Marketing Research 12th Edition 29End of Chapter Twelve