It all depends: Interaction terms in regression
If the effect of an independent variable on the response variable depends on some other variable, then you are in interaction land. When does a study question call for interaction terms? What does a categorical variable interacting with a categorical variable mean? And how about two continuous variables that interact, and continuous with categorical variable interactions? How can I interpret my results if my interaction was significant/ not significant? We’ll look at lots of ways to plot out the results of a regression that has included an interaction between 2 (or more) variables.
The talk will be about 30 minutes long and follow by discussion.
Speaker: Eve Slavich, Statistical Consultant, UNSW Stats Central
Date: Thursday 29 April 2021