Hierarchical Bayesian Model of Worker Response to Proximity Warnings of Construction Safety Hazards: Toward Constant Review of Safety Risk Control Measures

Quickly changing and complicated workplace conditions, which are typical of construction projects, have always been contributing to the poor safety record of the construction industry. However, few of the existing approaches to reviewing control measures take into account or effectively tackle these conditions. This paper introduces a three-level (i.e., individual hazards, hazard types, and generic hazards) hierarchical Bayesian model based on workers' responses to proximity warnings of safety hazards to address the problem. The proposed model distinguishes between two uses of proximity warnings (i.e., as the primary control measure and as the secondary measure), uses observational response rates as input, takes into account prior knowledge of workers' responses to similar hazards, and produces estimated response rates (ERRs). These ERRs are the primary indicator of the effectiveness of a given control measure as well as of the validity of a previously identified safety hazard. A 17-day field experiment was conducted to test the proposed approach, preliminarily using a location-based proximity warning system to warn workers of safety hazards and record their responses to warnings. The experimental results demonstrated the potential of the proposed approach. The limitations of the present analysis and the directions for future research are also discussed.