Visual Heuristics for Marginal Effects Plots

15 Pages Posted: 14 Apr 2017  

Thomas B. Pepinsky

Cornell University - Department of Government

Date Written: April 13, 2017

Abstract

Common visual heuristics used to interpret marginal effects plots are susceptible to Type-1 error. This susceptibility varies as a function of (1) sample size, (2) stochastic error in the true data generating process, and (3) the relative size of the main effects of the causal variable versus the moderator. I discuss simple alternatives to these standard visual heuristics that may improve inference and do not depend on regression parameters.

Keywords: interaction terms, marginal effects

Suggested Citation

Pepinsky, Thomas B., Visual Heuristics for Marginal Effects Plots (April 13, 2017). Available at SSRN: https://ssrn.com/abstract=2952326 or http://dx.doi.org/10.2139/ssrn.2952326

Thomas B. Pepinsky (Contact Author)

Cornell University - Department of Government ( email )

Ithaca, NY 14853
United States

Paper statistics

Downloads
268
Rank
92,478
Abstract Views
502