1. In addition to exercising in an aerobics class, the exercise group leaves their residences and has contact with others during the class, whereas the relaxation group stays in and has no contact with others. In other words, exercise is confounded with getting out and interacting with others, which may be instrumental in reducing depression.

2. (a) selection; (b) history and maturation; (c) statistical regression.

3. First-year students may be more likely than upperclass students to experience maturational changes that produce improvement in writing skills. Therefore, differences in writing improvement between the writing-intensive and other students may not be due to their experience in the course but rather to the selection of groups for the experimental conditions that differ in their susceptibility to a maturation effect.

4. (a) This is a pretest-posttest design:

X represents the treatment, DARE; O1 represent the pretest measure of attitude toward drugs and O2 represents the posttest measure.

The problem with this design is that children’s attitude toward drugs may change between the pretest and posttest even if they weren’t exposed to DARE. The two principal threats to validity are maturation and history, although a testing effect also is plausible. A maturation effect may occur insofar the children may develop psychologically, becoming more aware of their bodies and of the unhealthy effects of ingesting drugs; or, alternatively, they may be growing through a stage when they are more likely to challenge adult authority by experimenting with drugs. A history effect may occur insofar as events may occur outside the DARE program, in the school or community, which influence the children’s attitude toward drugs. For example, a fellow student may have been arrested or suffered serious effects from drug use or an anti-drug campaign may be undertaken in the media. Testing could be a factor insofar as the pretest changes the way that students respond to the posttest; for example, becoming aware of what is being measured, students may be more inclined on the posttest to conceal more favorable attitudes toward drug use.

(b) This is a static group comparison:

X represents the treatment, DARE; O1 represent the posttest measure of attitude toward drugs among students in the district classes exposed to DARE, and O2 represents the posttest measure in the district classes not exposed to DARE.

The principal threat to the validity of this design is selection. It is very possible that the two districts differ in many ways that may affect students’ attitude toward drugs. In addition, history and differential attrition are possible threats. A history effect could occur if the students in the two districts are exposed to particular influences that affect their attitudes in different ways. Differential attrition could be a problem if a large number of students in one of the two school districts drop out of school and if these students happen to differ from others in their attitudes toward drug use.

(c) Researchers would need to have control over (1) the assignment of children to the DARE program, which should be based on randomization rather than self-selection; (2) the administration of the DARE program, so that the treatment is the same in every class in which it is used; (3) other classes and events in the schools, so that the students in the treatment and control conditions have similar experiences; and (4) the administration of the “tests” or measures of the dependent variable. Ideally, the experiment should be run within the same schools rather than across schools; that is, students in the same schools should be randomly assigned to treatment (DARE) and control conditions.

5. This outcome would look like Figure 8.2.D in the textbook.