Question

A school counselor in a high school would like to try out a new conflict-resolution program to reduce aggressiveness in students. She first surveyed 16 students using a 20-item instrument to measure their levels of aggression (on a scale of 0 to 10, with higher numbers meaning higher aggression levels). One month after the conflict resolution program was implemented, the students were given the same survey. The data are listed in the table below. The school counselor/researcher has set the significance level at α = .05.

	Aggressiveness rating
Subject	Before program	After program
1	6	4
2	2	3
3	3	1
4	5	5
5	7	7
6	4	4
7	2	3
8	4	3
9	2	1
10	8	3
11	3	3
12	5	4
13	5	4
14	8	4
15	6	7
16	1	4

d) Estimate the standard deviation of the comparison population (that represents the null hypothesis)

e) Calculate the standard error (standard deviation of the sampling distribution)

f) Calculate the raw and standardized effect size of this hypothesis test

The school counselor could also set up the hypothesis to merely test for a difference in the level of aggressiveness, without specifying a direction. In other words, the school counselor might not be sure if the program will reduce aggression or if it might actually heighten aggression for some unforeseen reason.

b) Since a non-directional hypothesis is examined with a two-tailed test, determine the critical t values for the two-tailed test using the same alpha level and degree of freedom.

c) Compare the t statistic with the critical t values. Is the calculated t statistic more extreme or less extreme than either of the critical t values? What is the decision of the hypothesis test now?

Answer 1