Dealing with Endogeneity in Mediation and Multilevel Models

Social scientists across many fields often rely on quantitative survey data to test relationships between predictor and outcome variables. When predictors are measured rather than experimentally manipulated, there is the risk of endogeneity. Endogeneity refers to one (or more) of the predictors relating to the outcome variable for reasons other than any causal effect it would have on that outcome. Common reasons for endogeneity include the predictor and outcome sharing an unmeasured common cause, and the outcome being a cause of the predictor.  If endogeneity is not addressed, then regression coefficients can be severely biased.

This hands-on two-day workshop will walk participants through the steps needed to deal with endogeneity methodologically and statistically. It is meant for individuals already familiar with experimental research design, the general linear model (e.g., multiple regression). Day 1 will focus on endogeneity in statistical models involving a mediating variable. Day 2 will address endogeneity in multilevel (or hierarchical linear) models, such as those involving panel or repeated measures data. Familiarity with specific statistical software is not required.

METHODOLOGY EXPERT

John Antonakis, Professor of Organizational Behavior in the Faculty of Business and Economics of the University of Lausanne, Switzerland

John Antonakis is Professor of Organizational Behavior in the Faculty of Business and Economics of the University of Lausanne, Switzerland. Professor Antonakis’ research is currently focused on leadership and applied econometrics and psychometrics. He has published articles in many prestigious journals including Science, Nature Human Behavior, Psychological Science, Academy of Management Journal, Journal of Management, Journal of Applied Psychology, Journal of Operations Management, Entrepreneurship Theory and Practice, and Harvard Business Review, among many others. He has received more than US$2.8 million in funding for his research. Prof. Antonakis is Editor of The Leadership Quarterly. In 2019 he was named a highly cited scientist by Clarivate-Web of Science group; he has also been named a top-2% career highly cited scientist by Ioannidis et al. (PLOS Biology, 2020). His research is regularly quoted in the press and various media outlets.