Determinants of Safety Outcomes in Organizations: Exploring O*NET Data to Predict Occupational Accident Rates
Abstract
Workplace safety is of utmost importance given the regular occurrence of both fatal
and nonfatal occupational injuries all around the world. Although research in this
area is hugely prevalent, it is focused mainly on safety climate and lacks an
integrated approach when examining predictors of safety outcomes. The
development of an occupational risk factor that predicts safety outcomes will aid in
understanding the relative importance of different factors that contribute to safety
and help organizations target their safety programs and interventions efficiently.
The present study is an exploratory analysis utilizing publicly available O*NET
data (work activities, work context features, and worker characteristics) to predict
annual occupational injury and illness incident rates (nonfatal) published by the
U.S. Bureau of Labor Statistics. The use of statistical learning methods (LASSO,
random forest, and gradient boosting) for analysis using Python also helped
compare results to those obtained by past research utilizing traditional statistical
methods. Findings indicate that the O*NET descriptors related to work, work context,
and to a lesser extent worker characteristics were indeed significant in predicting
nonfatal occupational injury/incident rates. The amount of variance explained in the
outcome by the predictors varied from 27.8% (gradient boosting) to 33.1% (random
forest) with 19 unique predictors across the three machine learning methods. This
study adds to the literature surrounding person and situation-based antecedents to
workplace safety, presents a huge step toward the development of a cross-occupational risk factor, and has several other implications for research and
practice.