In: Statistics and Probability
4. Why would a researcher test a one-tailed vs. a two-tailed hypothesis?
5. Why would it be impossible for a researcher to test the following hypothesis using a t-test? H1: Female homicide offenders are more likely to be sentenced to maximum security prison than male homicide offenders.
6. If the null hypothesis in a t-test for two samples is not rejected, what conclusion can be drawn about the two means of the categorical variable?
7. Two groups of subjects participated in an experiment designed to test the effect of frustration on aggression. The experimental group of 40 subjects received a frustrating puzzle to solve, while the control group of 70 subjects received a very easy version of the same puzzle. Levels of aggression was measured for both groups where higher scores are indicative of higher levels of aggression. The experimental group (high frustration) had a mean aggression score of 4.0 and a standard deviation of 2.0. The control group (no frustration) had a mean aggression score of 3.0 and a standard deviation of 1.5. Using these results, formulate a research and null hypothesis and test the null hypothesis at the .01 level of significance.
8. Assume you collected larger samples of individuals to test your null hypothesis in question #7. Specifically, the sample sizes increased to 200 subjects in each group. Do your results and conclusions change from the test of the smaller sample sizes?