Answers to Practice Questions for Final:
Part II: Application:
NOTE: Use the Which Test handout to help you. Identify the variables and their nature, see if you can figure out how many samples/groups there are, and that should help you narrow the choices down. The key variables should appear in the research question.
1. c, there are two separate samples (AIDS education, yes or know) and a quantitative DV
2. d, there is one sample of men, with two scores each, quantitative DV
3. i, variable is categorical, people classified into three categories, question is about equal proportions
4. h, two IVs (sex, region) and single quantitative DV (glasses of milk)
5. e, question about relation between two quantitative variables measured on same person (Rob). NOTE: Oops! Research Q should be about relation between Rob's mood and days since breakup, not Dan's mood. Sorry.
6. b, one sample, myuu is known for the comparison population, but sigma is not
Note: The research question should help you narrow down to t-test (or possible z-test). Then look more closely at how the data was collected, and whether population mean and variance are known for the comparison population. Second note: Don't get confused about the nature of the variables. Nightmares are being counted, but that doesn't mean that you should select a chi-square. If each person was classified into "has nightmares" or "doesn't have nightmares" that would be categorical. Instead, nightmares is treated as a quantitative variable (ratio scale of measurement)
7. k, two categorical variables (weather, hot/cold food) have counts of people classified into two sets of categories, association question
8. f, prediction of one variable from knowing the value of the other [Note: for this scenario, the regression procedure is not a "test" in the same way as the other procedures are tests of hypotheses--instead it's a strategy for prediction]
9. a, mu and sigma are known for one population, and you have a sample mean for a single sample from other population
10. g, quantitative DV, more than two levels of a single IV
11. j, categorical variable, question about whether proportions differ from a comparison population