A researcher randomly sampled 30 graduates, 18 males and 12 females, of an MBA program and recorded data concerning their starting salaries. Of primary interest to the researcher was the effect of gender on starting salaries. Statistics of the mean salaries of the females and males in the sample were computed. The sample standard deviations suggest that the variability of starting salaries of the two groups is almost the same. Suppose the starting salaries from both groups can be considered as normally distributed. Which of the following tests will be the most appropriate?
A) Wilcoxon signed rank test
B) separate-variance t test
C) pooled-variance t test
D) paired t test

Question

Quizplus · Accepted Answer

A pooled-variance t test is appropriate for comparing the means of two independent groups when their variances are assumed to be equal and their distributions are approximately normal. This is the case for the data presented in the scenario. The other test options are not appropriate in this context. The Wilcoxon signed rank test is used for paired data and non-parametric data, neither of which applies here. The separate-variance t test is appropriate when the variances of the two groups are not assumed to be equal, but in this scenario, it is stated that the sample standard deviations suggest the variability of the two groups is almost the same. The paired t test is for paired data, which also does not apply to this scenario where the two groups are independent.

A Researcher Randomly Sampled 30 Graduates, 18 Males and 12