Question

A counseling psychologist is interested in three types of therapy for modifying snake phobia. However, she does not believe that one type of therapy is necessarily best for everyone; instead, the best type might depend on the severity of the phobia. Undergraduate students enrolled in an introductory psychology course who volunteer are given the Fear Schedule Survey (FSS) to screen out those who show no fear of snakes. Those displaying some fear are classified as either mildly, moderately, or severely phobic on the basis of the FSS. One third of subjects within each level of severity are randomly assigned to a treatment condition (treat): systematic desensitization (des), implosive therapy (impl), or insight therapy (insig). After the end of treatment, each participant completes the Behavioral Avoidance Test (high scores indicate a better outcome, less phobic). 1. Which of the following best describes the study design being used in this study? a. 2. The F test for the factor treatment (treat) would be described as which type of test? a. 3. The mean square (MS) values have not been included in the output, what is the MS value for the severity factor? a. 4. In terms of interpreting the interaction effect, which table of means would be of most interest? 5. Based on the ANOVA table presented in graph 27, which of the effects in this analysis would be considered statistically significant using .01 as the alpha level? 6. If a statistically significant interaction effect is found, which of the following might be done to further explain the interaction effect?

Answer 1

3. The mean square (MS) values have not been included in the output, what is the MS value for the severity factor?

4 . In terms of interpreting the interaction effect, which table of means would be of most interest?

5. Based on the ANOVA table presented in question 27, which of the effects in this analysis would be considered statistically significant using .01 as the alpha level?

6. If a statistically significant interaction effect is found, which of the following might be done to further explain the interaction effect?

3)

MS = SS/df = 235.244/2 = 117.622

4)

last table treat:severity would be of most interest

5)

if p-value < alpha, then that factor is significant

here alpha = 0.01

hence severity and interaction are considered statistically significant as their p-values are less than 0.01

6)

To determine exactly which parts of the interaction are significant, the omnibus F test must be followed by more focused tests or comparisons.

Method 1. One way ANOVA

Method 2. Post Hoc Tests

Method 3. Simple Effects Tests

Method 4. Planned Comparisons