Abstract
The purpose of this study was to test a nonlinear model of psychological well-being at work. Specifically, artificial neural networks (ANNs) were used to identify and map nonlinearities among supervisor support, control over work methods and employee well-being. Our findings confirmed results from prior studies in that ANNs explained significantly more variance in well-being than did OLS regression. Visualization of nonlinear relationships extended prior research, demonstrating strong patterns of nonlinearity between two dimensions of supervisor support, direct support and trust, and well-being. Discussion was focused on the implications of observed nonlinearities for theory development and on the value of ANNs in building more accurate predictive models of employee well-being.
Disclosure statement
No potential conflict of interest was reported by the author(s).