Using Bayesian Dominance Hierarchies to Determine Predictor Importance in Service Research Predictive Studies

Abstract

Empirical results in business research derived from multiple linear regression models are often susceptible to issues of dimensionality and multicollinearity. We extend the current research practices for addressing multicollinearity by introducing an original method, Bayesian Dominance Hierarchy (BDH) to determine the relative importance of predictors in a multiple regression context.