Supplementing Interaction: Simple Effects (3 of 3)
Next section: Components of interactions
Some researchers have the misconception that testing simple effects is necessary for understanding the interaction. This is not true since the interaction is interpretable in its own right. The rationale for testing simple effects, rather, is simply that sometimes it is important to know at what levels of a second variable the variable in question has a significant effect. Testing simple effects is done following an interaction not to help understand the interaction, but rather to see where the effect of the variable is significantly different from zero.
Next section: Components of interactions