Premium
Thinking differently: Assessing nonlinearities in the relationship between work attitudes and job performance using a Bayesian neural network
Author(s) -
Somers Mark John
Publication year - 2001
Publication title -
journal of occupational and organizational psychology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.257
H-Index - 114
eISSN - 2044-8325
pISSN - 0963-1798
DOI - 10.1348/096317901167226
Subject(s) - artificial neural network , perspective (graphical) , nonlinear system , psychology , machine learning , work (physics) , bayesian probability , job performance , artificial intelligence , social psychology , computer science , job satisfaction , engineering , mechanical engineering , physics , quantum mechanics
The relationship between work attitudes and individual job performance was investigated using artificial neural networks (ANNs). ANNs use pattern recognition algorithms that are well suited to capturing nonlinear relationships among variables thereby providing a new perspective on research on this topic area. Results from the neural network analysis provided strong evidence of nonlinearity suggesting that nonlinear models are needed to understand the work attitude‐job performance relationship. In so doing, the neural network model had greater predictive accuracy than did traditional OLS regression. Implications of this finding for theory development and future research were discussed.