# Question: Consider the following actual data from a study by Lyon

Consider the following actual data from a study by Lyon & Greenberg (1991). The first factor in their factorial ANOVA was family background; female participants were classified into two groups (group 1, “Codependent”, women with fathers who have alcoholism; group 2, “Noncodependent”, women with fathers who do not have alcoholism). Members of these two groups were randomly assigned to one of two conditions; they were asked to donate time to help a man who was described to them as either “Mr. Wrong” (exploitative, selfish, and dishonest) or “Mr. Right” (nurturant and helpful). The researchers predicted that women from a non-codependent/non-alcoholic family background would be more helpful to a person who was described as nurturant and helpful, whereas women from a codependent/alcoholic family background would be more helpful to a person described as needy and exploitative.

The table of means below represents the amount of time donated in minutes in each of the four cells of this 2 x 2 factorial design. In each cell, the first entry is the mean, and SD is given in parentheses. The number of scores within each group or cell was 12.

The reported F ratios were as follows:

FA(1,44) = 9.89, p < .003

FB(1,44) = 4.99, p < .03

FAxB(1,44) = 43.64, p < .0001

a. Calculate an 2 effect size for each of these effects (A and B main effects, and the A x B interaction).

b. Calculate the row means, column means, and grand mean from these cell means.

c. Calculate the αi and βj effects for each level of A and B.

d. For each cell, calculate the αβij interaction effect

e. Set up a table that summarizes these effects (similar to Table 13.4).

1f. Write up a Results section that presents these findings and provides an interpretation of the results.

1g. What were the values of the 12 individual scores in the A2/B1 group? How do you know?

The table of means below represents the amount of time donated in minutes in each of the four cells of this 2 x 2 factorial design. In each cell, the first entry is the mean, and SD is given in parentheses. The number of scores within each group or cell was 12.

The reported F ratios were as follows:

FA(1,44) = 9.89, p < .003

FB(1,44) = 4.99, p < .03

FAxB(1,44) = 43.64, p < .0001

a. Calculate an 2 effect size for each of these effects (A and B main effects, and the A x B interaction).

b. Calculate the row means, column means, and grand mean from these cell means.

c. Calculate the αi and βj effects for each level of A and B.

d. For each cell, calculate the αβij interaction effect

e. Set up a table that summarizes these effects (similar to Table 13.4).

1f. Write up a Results section that presents these findings and provides an interpretation of the results.

1g. What were the values of the 12 individual scores in the A2/B1 group? How do you know?

## Answer to relevant Questions

How does Type III sum of squares differ from Type I sum of squares in GLM? If there is a statistically significant interaction: how can you remove the main effects of A and B from the cell means in order to see the interaction effects alone more clearly? What can the residuals from a regression tell us about possible violations of assumptions for regression? What information do we need to assess possible multicollinearity among predictors? What is a quasi-experimental design? What is a nonequivalent control group?Post your question