The Estimation of Reservation Wages: A Simulation-Based Comparison

This paper examines the predictive power of different estimation approaches for reservation wages. It applies stochastic frontier models for employed persons and the approach from Kiefer and Neumann (1979b) for unemployed persons. Furthermore, the question of whether or not reservation wages decrease over the unemployment period is addressed. This is done by a simulated panel with known reservation wages which uses data from the Socio-Economic Panel as a basis. The comparison of the estimators is carried out by a Monte Carlo simulation. In case of employed persons, the cross-sectional stochastic frontier model shows the best performance. The Kiefer-Neumann approach for unemployed persons is able to predict decreasing reservation wages but the rise of the mean reservation wage in case of a constant simulated reservation wage went undetected. In general, the Kiefer-Neumann approach overestimates the reservation wage.