Chapter 4.docx

6 Pages
Unlock Document

University of Guelph
Marketing and Consumer Studies
MCS 3030

Chapter 4 – Survey Research Constructing The Survey -primary issues involved in writing a question: -determining question content, scope and purpose -choosing response format that you use for collecting information from respondent -figuring out how to word the question to get at the issue of interest Types of Questions: ●Dichotomous question- a question with two possible responses -yes/no, true/false, agree/disagree ●Questions based on level measurement nominal response format- has a number beside each choice where the number has no meaning except as a placeholder for that response ordinal response format-respondents are asked to rank the possible answers in order of preference. Interval-level response format-response measured on interval level, where the size of interval between potential response values is meaningful (most 1 to 5 rating responses considered interval level) Semantic differential-scaling method in which the respondent assesses an object on a set of bipolar adjective pairs Guttman scale-respondents check each item with which they agree (usually cumulative-if agree with one of them, usually agree with all above it in same list) Filter or contingency question- respondents to determine whether they are qualified or experienced enough to answer a subsequent one -try to avoid more than three levels for any one question (too many will confuse respondents and may discourage them for continuing with survey) -if there are only two levels, use graphics to jump -if possible, jump to a new page (if yes, turn to page 4 rather than go to question 38) Question Content -each question should address content you are trying to get at -question should be necessary and useful -sometimes several questions are needed (so too many things are not asked at once) double-barreled question-when a question asks two questions in one -ensure respondent has necessary information to answer question (can’t expect respondents know what your asking) -ask specific questions (sometimes can be too specific) Biased or loaded question-own biases may affect working -ensure questions are ones which respondents will answer truthfully (can use response brackets-between 30 and 40 years old) Response Format Response format-how you collect answer from respondent ●Structured response format- determined prior to administration -help respondent respond more easily and help researcher accumulate and summarize responses more efficiently -can constrain respondent and limit researchers ability to understand what respondent really means Fill-in-the-blank- one of simplest formats st nd rd -can be a check mark or a ranking (1 , 2 , 3 , etc. choice), writing in a blank (ie. Name) Check the answer-respondent checks off their response Multioption variable-respondents can check multiple variables from a list -want to ensure all alternatives are covered, list is reasonable length, wording is impartial, form of response is easy and uniform -if not sure all possible responses in checklist are covered you should allow respondent to write any other options that apply Circle the answer-respondents circle answer ●Unstructured response format- not predetermined and where the response is determined by the respondent. (ie. open-ended question) -generally written text Question Wording -slightest wording differences can confuse the respondent or lead to incorrect interpretations of question -ensure questions are not going to be misunderstood -sure there are no assumptions in the question -make sure that you specify the time frame precisely -ensure wording is objective and appropriate for context -make sure wording is not too direct (which could be taken as threatening or disturbing) -shouldn’t contain difficult or unclear terminology -should make alternative clear -shouldn’t be loaded or slanted (don’t direct respondent to specific response) Question Placement -ordering of questions is important -important questions at end may get little attention if respondents get tired of survey -respondents may not be able to answer important questions addressed too early -when thinking about question placement consider: -answer may be influence by prior question -question may come too early or too late to arouse interest -question may not receive sufficient attention because of questions around it -never start mail survey with open-ended question -for historical demographics, follow chronological order -ask about one topic at a time -when switching topics, use transition -reduce response set (tendency of respondent to just keep checking the same response) -for filter contingency questions, make flowchart Opening Questions-first impressions are important in survey-determine tone and help put respondent at ease -should be general and easy to answer -never begin with threatening or sensitive questions Sensitive Questions-before asking sensitive question, should develop trust or rapport with respondent -must consider ethical aspects of study -put more difficult, threatening questions near end Golden Rule-do unto respondents as you would have them do unto you -thank respondent at beginning for allowing you to conduct survey -keep survey as short as possible-include only what’s necessary -be sensitive to needs of respondent -be alert for any sign that respondent is uncomfortable -thank respondent at end for participating -assure respondent that you will send them copy of final results
More Less

Related notes for MCS 3030

Log In


Don't have an account?

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Sign up

Join to view


By registering, I agree to the Terms and Privacy Policies
Already have an account?
Just a few more details

So we can recommend you notes for your school.

Reset Password

Please enter below the email address you registered with and we will send you a link to reset your password.

Add your courses

Get notes from the top students in your class.