Terms in this set (60)

What does the graph of an interaction effect look like? What does the graph of a main effect look like if there are no interactions?
Explain why the presence of an interaction limits the interpretation of the main effects in a two-factor study.
Main effect: causal effect of each independent variable tests differences between all means for each level of an independent variable in an analysis of variance (ANOVA)
the effect of a single independent variable on a dependent variable - while ignoring all other independent variables
Interaction effect: tests the effect of one independent variable for each level of another independent variable
means that change in the dependent variable cannot be explained by independent effects of the two factors - the effect of one factor depends on what has happened to the other factor
Graph of interaction effect: the lines on the graph will intersect, lines are not parallel
Graph of main effect: the lines on the graph will not intersect, lines are parallel will show that the mean of one level for a factor is higher than another level for same factor
For example:

This shows both an interaction b/w Condition and Group and main effects for both Condition and Group
If you take the mean of condition A (in between Condition A, Group 1 and Condition A, Group 2) compared to the mean of Condition B (same procedure as before), you'll note that the mean of Group A < mean Group B → main effect exists for Condition
You can do the same procedure to discover the main effect for Group
For the interaction: easy, the lines aren't parallel → there exists an interaction
Regarding why the presence of an interaction limits the interpretation of main effects: When two factors interact, it means that changes in the dependent variable cannot be explained by independent effects of the two factors. Rather, the explanation must be more complicated. The effect of one factor depends on what has happened to the other factor.
So basically: an interaction means we must shift our attention from how does _ factor influence the dependent variable to how changes in one factor relate to changes in another factor in affecting the dependent variable
;