Exercises and Discussion Questions
9.1 Imagine the following situation. A friend of yours is running for a place on the local school board. You agree to help her by surveying local voters to learn which issues are most important to them and what they would like the school board to do. How will you obtain a sample for this survey?
This, of course, is the question we asked at the start of the book. Since then, you have learned a lot. You have learned how to define the population of interest, how to recognize and fix problems with the sampling frame, how to draw the sample, and ways to address potential non-response bias. You have learned how to set a sample size, and how to use stratification or clustering to enhance the cost-effectiveness of your research. You have learned how to weight data if appropriate, and how you might use models for estimation purposes. You have learned about sampling in a variety of special contexts. More generally, you have become familiar with the ideas of sample bias and sampling error and the methods used to control them. At this point, you should be able to recognize how your results may be affected by the nature of the sample, and you should be able to make good decisions about sampling, so we will leave you on your own to answer this question. Best wishes.