Regression as the Univariate General Linear Model: Examining Test Statistics, P-Values, Effect Sizes, and Descriptive Statistics Using R

• In Event: 32.067 - Multiple Linear Regression: The General Linear Model SIG Paper Session: Special Adaptations of the General Linear Model to Best Reflect the Research Question

Abstract

This paper presents regression as the univariate general linear model (GLM). Building on the work of Cohen (1968) and Zientek and Thompson (2006), the paper uses descriptive statistics to build a small simulated dataset that readers can use to verify that multiple linear regression (MLR) subsumes the univariate analyses in the GLM. Unlike other related works, we provide R syntax that demonstrates, in general, how multiple linear regression (MLR) provide similar test statistics, p-values, effect sizes, and descriptive statistics when compared to the univariate analyses that MLR subsumes. The paper also considers the special case of the chi-square test where p-values diverge when run as MLR.

Authors

• Kim Nimon, The University of Texas - Tyler

• Julia Berrios

• Mandolen Mull

• Jon Musgrave, Indiana State University

• Gregg Keiffer, Houston Baptist University