Workshop conducted for the Society for Industrial and Organizational Psychology (SIOP) Membership Committee (virtual)—June, 2023

Presenter

Rick A. Laguerre, PhD - Assistant Professor at Montclair State University

Workshop Title

Rank Ordering Predictors with Dominance Analysis: Leveraging the Correlation Matrix

Abstract

Organizational scientists are increasingly striving to determine the “best predictor” of workplace phenomena, but our most popular techniques (e.g., multiple regression, structural equation modeling, etc.) are limited in their ability to determine the relative importance of predictors. These limitations have to do with our use of significance testing, the inclusion of control variables, and common misconceptions about the interpretation of regression-based results. Therefore, the purpose of this workshop is to introduce users to the dominance analysis technique for determining the relative importance of predictors—a clear and easy way to rank order predictors and ascertain which predictor is truly the “best” in a given model. In this workshop, we will discuss: a) what a dominance analysis is and how to do one via hands-on demonstrations in R, b) the advantages of using a correlation matrix as the data source when doing the procedure, and c) how researchers and practitioners can leverage the technique to increase methodological rigor without adding statistical complexity. The presenter has published on the topic of dominance analysis and has used it in empirical research. Workshop attendees will be provided with R code, a sample dataset, and an exercise to help learn the technique.

Relevant citations:

Budescu, D. V. (1993). Dominance analysis: A new approach to the problem of relative importance of predictors in multiple regression. Psychological Bulletin, 114(3), 542–551. https://doi.org/10.1037/0033-2909.114.3.542

Laguerre, R. A. (2021). Evaluating hypotheses with dominance analysis. Industrial and Organizational Psychology, 14(4), 514–517. https://doi.org/10.1017/iop.2021.109