RWA Web: A Free, Comprehensive, Web-Based, and User-Friendly Tool for Relative Weight Analyses

• Published in: Journal of business and psychology 2015-06, Vol.30 (2), p.207-216
• Main Authors: Tonidandel, Scott, LeBreton, James M.
• Format: Article
• Language: English
• Subjects: Behavioral Science and Psychology; Bootstrap method; Business and Management; Community and Environmental Psychology; Industrial and Organizational Psychology; Occupational psychology; Organization theory; Personality and Social Psychology; Psychological aspects; Psychology; Regression analysis; Researchers; Social Sciences; Studies; Variables
• ISSN: 0889-3268; 1573-353X
• DOI: 10.1007/s10869-014-9351-z

Over the last 15 years, a number of methodological developments have enabled researchers to draw more accurate inferences concerning the relative contribution (i.e., relative importance) among multiple (often correlated) predictor variables in a regression analysis. One such development has been relative weight analysis (RWA). Researchers can use a RWA to decompose the total variance predicted in a regression model (R²) into weights that accurately reflect the proportional contribution of the various predictor variables. Prior to RWA, researchers were forced to rely on traditional statistics (e.g., correlations; standardized regression weights), which are known to yield faulty or misleading information concerning variable importance (especially when predictor variables are correlated with one another, which is often the case in organizational research). Although there has been a surge of interest in RWA over the last 10 years, integration of this statistical tool into organizational research has been hampered by the lack of a user-friendly statistical package for implementing RWA. Indeed, most popular statistical packages (e.g., SPSS, SAS) have yet to include RWA protocols into their regression modules. The purpose of this paper is to present a new, free, comprehensive, web-based, user-friendly resource, RWA-Web, which may be used by anyone having simple access to the internet. Our paper is structured as a tutorial on using RWA-Web to examine relative importance in the classic multiple regression model, the multivariate multiple regression model, and the logistic regression model. We also illustrate how RWA-Web may be used to conduct null hypothesis significance tests using advanced bootstrapping procedures.