Statistical Methods for Psychology

Older/Low: 98681046577

Older/High: 101914 5101114151111

a. Run a one-way analysis of variance on these data.

b. Now run a one-way analysis of variance on treatments 1 and 3 combined (n 5 20)

versus treatments 2 and 4 combined. What question are you answering?

c. Why might your answer to part (b) be difficult to interpret?

11.4 Refer to Exercise 11.1. Assume that, for reasons beyond our control, neither the data for the
last pup in the 5-day group nor the data for the last two pups in the 35-day group could be
used. Rerun the analysis of variance with the remaining data.

11.5 Refer to Exercise 11.2. Suppose that we collected additional data and had two more sub-
jects in the Younger group, with scores of 13 and 15.
a. Rerun the analysis of variance.
b. Run an independent groups t test without pooling the variances.
c. Run an independent groups t test after pooling the variances.
d. For (b) and (c), which of these values of t corresponds (after squaring) to the Fin (a)?

11.6 Calculate and for the data in Exercise 11.2. Would you assume a fixed or a random
model?

11.7 Calculate and for the data in Exercise 11.3.

11.8 Foa, Rothbaum, Riggs, and Murdock (1991) conducted a study evaluating four different
types of therapy for rape victims. The Stress inoculation therapy (SIT) group received in-
structions on coping with stress. The Prolonged exposure (PE) group went over the events
in their minds repeatedly. The Supportive counseling (SC) group was taught a general
problem-solving technique. Finally, the Waiting list (WL) control group received no ther-
apy. The data follow, where the dependent variable was the severity rating of a series of
symptoms.
Group n Mean S.D.
SIT 14 11.07 3.95
PE 10 15.40 11.12
SC 11 18.09 7.13
WL 10 19.50 7.11

a. Run the analysis of variance, ignoring any problems with heterogeneity of variance,

and draw whatever conclusions are warranted.

b. Apply Welch’s procedure for heterogeneous variances. Does this affect your conclusions?

c. Draw a graph showing the means of the four groups.

d. What does rejection of mean in this case?

11.9 Calculate and for the data in Exercise 11.8 and interpret the results.

11.10 What would happen if the sample sizes in Exercise 11.8a were twice as large as they actu-
ally were, but all other statistics remained the same?

11.11 The computer printout in Exhibit 11.4 is from a JMP analysis of the data in Exercise 11.8.

a. Compare the results with those you obtained in Exercise 11.8a.

b. What can you tell from this printout that you cannot tell from a standard summary

table?

h^2 v^2

H 0

h^2 v^2

h^2 v^2

Exercises 357