Nuclear power plant safety. An article in the American Journal of Political Science (January 1998) examined the attitudes of three groups of professionals that influence U.S. policy. Random samples of 100 scientists, 100 journalists, and 100 government officials were asked about the safety of nuclear power plants. Responses were made on a seven-point scale, where 1 = very unsafe and 7 = very safe. The mean safety scores for the groups are scientists, 4.1; journalists, 3.7; government officials, 4.2.
(a) Identify the response variable for this study.
(b) How many treatments are included in this study? Describe them.
(c) Specify the null and alternative hypotheses that should be used to investigate whether there are differences in the attitudes of scientists, journalists, and government officials regarding the safety of nuclear power plants.
(d) The MSE for the sample data is 2.355. At least how large must MST be in order to reject the null hypothesis of the test of part a using α = .05?
(e) If the MST = 11.280, what is the approximate p-value of the test of part a?
(f) Determine the number of pairwise comparisons of treatment means that can be made in this study.
(g) Using an experimentwise error rate of α = .05, Tukey's minimum significant difference for comparing means is .23. Use this information to conduct a multiple comparisons of the safety score means. Fully interpret the results.