Interactions in linear regression models, 2023

This video series is a demonstration of how to interpret statistical interactions in linear regression models. It was created as part of a statistics class for first-year psychology PhD students in 2023. It consists of seven videos listed on this page and in a Youtube playlist.

These videos approach the idea of a statistical interaction (moderation) from several angles. The goal is to leave students with an intuitive understanding of what an interaction is and practical exposure to several kinds of two-way interactions in R. Examples cover binary predictors, continuous predictors, and multicategorical predictors. Students will learn to adjust the reference point (zero point) of one predictor to facilitate interpretation of the conditional slope (simple slope) of the other predictor.

These videos are designed to be viewed in order. For example, later videos continue discussing hypothetical data examples from earlier videos. These videos also assume that students have a conceptual understanding of simple linear regression and some exposure to the lm function in R.

The R code files used in this video series are available here: Code for interactions and hypothetical data [zip]. I show some slides in the first and last videos. Those slides are available here: Interactions intro and conclusion slides [pdf]. Many of the slides will not make sense without the context given in the videos, and you do not need the slides to watch the videos.

List of Videos

The videos linked below are also available in a single Youtube playlist.

Part 1: Introduction to key concepts

Part 2: Practice thinking about linear transformations of a predictor

Part 3: Interaction between two binary variables

Part 4: Interaction between a binary variable and a continuous variable

Part 5: Interaction between two continuous variables

Part 6: Interactions involving multicategorical variables

Part 7: Conclusion and comparison to main effects