Comparative Analysis of Hedonic Wage and Discrete Choice Models in Valuing Job Safety

Abstract This is the first study to compare the hedonic wage and discrete choice models in the context of real job market choices. The hedonic wage method is the most widely adopted approach in estimating the value of marginal changes in mortality risks (or value of a statistical life, VSL). Alternatively, the discrete choice model offers a framework for valuing non-market goods, often used in choice experiments involving hypothetical job selection scenarios. This study employs both the hedonic wage and discrete choice models, using real market data from Taiwan‘s Panel Survey of Family Dynamics (PSFD 2016-2018), to examine workers‘ industry choices and infer their willingness to pay for job safety. By comparing the estimation results from the discrete choice model and the hedonic wage model, this study finds that the marginal willingness to pay (MWTP) for risk reduction estimated from discrete choice models is unreasonably large and therefore prefers the hedonic wage model in estimating the value of job safety. The findings of this study contribute to the literature comparing the hedonic model and the discrete choice model in evaluating environmental goods, which are mainly conducted using housing market data.