Lecture 9- Factorial Designs Flashcards
What is factorial design
Two or more predictor variables have been manipulated
What is n-way design (two-way design, three-way design)
The number of predictor variables manipulated
What’s an independent design
Different entities in all conditions
The parameter estimate (b) for the interaction quantifies
The size of the interaction
If the interaction term is significant we have
Significant moderation effect
The effect of one predictor is stronger at
Some levels of another predictor
In factorial designs the effect of one predictor is stronger in
Certain categories of the other predictor
The aov_4() function is from which package
The afex package
What does the aov_4() function do
- Creates type 3 sum of squares
- An easier option
- Automatically sets contrasts
- No parameter estimates, diagnostic plots or robust methods
What does lm() do
- Creates type 3 sum of squares
- A trickier option
- Manually set contrasts
- Easy parameter estimates, diagnostic plots and robust methods
It’s never sensible to interpret main effects in the presence of
A significant interaction effect
What is the statistical model for moderation
Predictor + moderator + predictor*moderator = outcome
The interaction term is
The product of two variables
Interaction = variable1*variable2
