Irwin and colleagues (2004) conducted a study on adherence to an exercise program. Participants were asked to attend a monthly group education program to help them change their exercise behavior. Attendance was taken and participants were divided into three categories: those who attended fewer than 5 sessions, those who attended between 5 and 8 sessions, and those who attended between 9 and 12 sessions. The researchers assessed the number of minutes of exercise per week for all participants. Assume that you plan to do Bonferroni post hoc comparisons if the ANOVA is statistically significant.

a. With a desired alpha level of 0.05 overall, what would the cutoff p value be for each comparison using a Bonferroni test?

b. With a desired alpha level of 0.01 overall, what would the cutoff p value be for each comparison using a Bonferroni test?

c. Using statistical software, we performed all of the possible pairwise independent-samples t tests on a subset of data that matches the sample means in the study (see Exercise 12.45); the actual p values (listed in the Sig. column in SPSS) associated with each of those tests appear below. Assuming an overall alpha level of 0.05, decide whether to reject or fail to reject the null hypothesis for each comparison.

Transcribed Image Text:

p = 0.041 = 0.001 <5 versus 5-8: <5 versus 9-12: p 5-8 versus 9–12: p = 0.060