1 SOCIAL SURVEY RESEARCH: AN OVERVIEW OF SURVEY RESEARCH PRINCIPLES FOR CONSUMERS AND DECISION MAKERS. SOME QUESTIONS YOU NEED TO ASK WHEN UNDERTAKING SOCIAL RESEARCH: What is (are) your research question(s)? (Be as precise as possible.) ! What are the key variables you need to collect information upon? (A measurement ! question.) What do you expect to find? (What is your hypothesis?) ! How will you test your hypothesis(es)? (How will you address your research question)? ! How will you measure the variables you have decided to examine? (This involves the ! issue of operationalization.) What is the best method for collecting data to address your research question? (Is ! survey research the best way of answering your question? This is a research design question.) Are there possibilities to use triangulation? (Can you collect data through multiple ! methods?; e.g., in addition to some form of survey research, can you make direct observations?, use available data?, can you engage in other forms of unobtrusive data collection?). What is the unit of analysis you are interested in? (E.g., individuals, groups, ! provinces). What population are you interested in generalizing to? (This is a different question ! than the previous one.) What is your sampling frame? ! What type of sampling procedure do you intend to employ? ! What size will your sample be? Why? ! What is your anticipated response rate? ! Is the main purpose of your research descriptive or explanatory? ! How will you analyze your data? !
2 Will you be doing univariate, bivariate, or multivariate analysis? ! What relevant sub-groups should you consider in your analysis? ! What comparison data is available. ! Are your findings mainly applied, or are there broader social trends, or theoretical ! explanations that may be relevant to consider? How will you present your findings? ! ISSUES RELATED TO SAMPLING Why Sample? ! Probability vs. Non-Probability Samples ! Population of Interest ! Sampling Frame ! Types of Random Samples ! Simple Random Sampling Systematic Sampling with a Random Start Stratified Random Sampling Multi-Stage Cluster Sampling Types of Non-Random Samples ! Purposive Samples Quota Samples Snowball Sample Available Subjects
3 ISSUES RELATED TO MEASUREMENT AND QUESTIONNAIRE CONSTRUCTION Questions vs. statements (e.g., likert scale type items). ! Open-ended vs. closed-ended questions. ! Avoid Double-Barrelled Questions. ! Respondents Must Be Competent to Answer. ! Questions Should be Relevant. ! Short Items Are Best ! Avoid Negative Items. ! Avoid Biased Items and Terms. ! Single vs. Multiple Indicators ! Reliability and Validity ! QUESTIONNAIRE FORMAT Formats for Responses ! Ordering of Questions !
4 FACTORS AFFECTING THE RESPONSE RATE OF MAIL SURVEYS Sponsorship ! Questionnaire Format and Colour. ! Cover Letter. ! Ease of Completing and Returning the Questionnaire. ! Inducements to Reply. ! The Characteristics of the Respondents. ! Type of Mailing. ! Follow-up Letters and Telephone Calls. ! Number and Timing of Follow-ups or Reminders. !
5 A SELECTED BIBLIOGRAPHY Babbie, Earl. 1994. The Practice of Social Research, 7th ed. Belmont, CA: Wadsworth. Bailey, Kenneth D. 1982. Methods of Social Research. Second Edition. New York: The Free Press. Converse, Jean M. and Stanley Presser. 1986. Survey Questions: Handcrafting the Standardized Questionnaire. Newbury Park, CA: Sage Publications. Dillman, D.A. 1978. Mail and Telephone Surveys: The Total Design Method. New York: Wiley and Sons. Dillman, Don A. 1991. "The Design and Administration of Mail Surveys." Annual Review of Sociology 17:225-249. Gray, George and Neil Guppy. 1993. Successful Surveys. Toronto: Harcourt Brace. Lee, Eun Sul, Ronald N. Forthofer, and Ronald J. Lorimer. 1989. Analyzing Complex Survey Data. Newbury Park, CA: Sage Publications. Miller, Delbert C. 1991. Handbook of Research Design and Social Measurement. Fifth Edition. Newbury Park, CA: Sage Publications Sudman, Seymour, and Norman Bradburn. 1982. Asking Questions: A Practical Guide to Questionnaire Design. San Francisco: Jossey-Bass.
Recommend
More recommend
