Bài giảng Chapter 9 Surveys, Questionnaires, and Polls

Chapter 9Surveys, Questionnaires, and PollsMost commonly used quantitative methodUsed for obtaining information about what people do, and respondents’ attitudes or characteristicsIn experimental, quasi-experimental, and descriptive research designs1What is a Survey?System for collecting comparable information across many peoplePaper-and-pencil self-administered or self-reportsFace-to-face Telephone Mail Computer-assisted2Designing a SurveyDevelop the research designEvaluate existing questionnaires/surveysRecommended over creating your ownHas undergone extensive testing and revisionMinor changes are okay; substantial changes will require that you pretest or pilot test the questionnaire3Writing Your Own QuestionnaireStart with literature reviewDesigning survey itemsStraightforwardOne complete thought written in sentence or question formatRespondent should know how to answerAvoid abbreviations and slang expressionsShorter items are better than long ones4Open QuestionsRespondents use their own words to respond Makes data less comparable and more difficult to interpretConsider what constitutes an adequate answerBuild that request into the questionUse a recall cue to draw participants’ attention to issue, topic, or timeframeRecord everything participant saysCode responses after all data are collected5Closed QuestionsRespondents given a question or statement and given a set of responses to select fromAll responses must be known in advanceCreates easily comparable responsesUse a recall cue or stimulus statement to draw participants’ attention to issue, topic, or timeframe6Response Sets for Closed QuestionsNominal or categorical responsesExhaustiveMutually exclusiveEquivalentLikert-type scales5- or 7-point scale Includes middle or neutral responseSemantic differential scalesBipolar adjectives anchor 7-point scale7Examples of Response Sets for Likert-Type ScalesVery oftenFairly oftenOccasionallyRarelyNeverVery positiveGenerally positiveMixedGenerally negativeVery negativeCompletely agreeGenerally agreeUnsureGenerally disagreeCompletely disagreeStrongly agreeAgreeUnsureDisagreeStrongly disagree8Pretesting the Survey or QuestionnaireAlso called pilot testingShould be done if you developed a questionnaire or modified an existing oneFour approaches Cognitive approachConventional Behavior codingExpert panel9Sampling Issues for SurveysSample size and response rate are not the sameResponse rate or return rate = number of people who provide usable responses after being asked to participateAcceptable response rates vary by survey techniqueMay be differences in those who choose to respond and those that don’t respondUnusable responses10Survey Reliability and ValidityInternal reliability must be computed for multiple item questionnairesCronbach’s alphaVaries from 0 to 1.00Generally .70 considered acceptableThree types of validity should be consideredContent validityFace validityConstruct validity11Analyzing Survey DataData of all participants combined to create a picture of the wholeOften limited to descriptive purposesData can test existing modelsData from closed questions Descriptive statisticsData from open questionsCategorized or content analyzed12