MKTG 3258 Lecture Notes - Lecture 20: Multiple Choice, Social Desirability Bias
8 Feb 2020
School
Department
Course
Professor
Document Summary
In-person: by telephone, by mail, by pick-up/self-administered, by e-mail/website popup. Steps to questionnaire design: you rarely will ever design a questionnaire from scratch, step 1: search for existing instruments in highly ranked articles that can be adapted. If they were published they have been statistically validated. Making up questions - should be avoided at all costs. One poorly worded question can invalidate an entire research project: step 2: adapt and merge existing questionnaires to achieve your needs. Then pilot amongst the target population to ensure maximum clarity. It is too late once the survey has been released to make changes. Types of questionnaires: dichotomous, multiple choice, rank order scaling, rating scale, constant sum, contingency, open ended. Dichotomous questions: dichotomous yes/no response, pros: quick, does not allow for ambiguous answers, cons: does not allow for a certain degree of sensitivity and differentiation. Contingency questions: a question that is answered only if the respondent gives a particular response to a previous question.
