Evaluating Alternative Representations Of The Choice Sets In Models Of Labor Supply

During the last two decades, the discrete choice modeling of labor supply decisions has become increasingly popular. Within the literature adopting this approach, however, there are two potentially important issues that so far have not been given the attention they might deserve. A first issue concerns the procedure by which the discrete alternatives are selected to enter the choice set. Most authors choose (not probabilistically) a set of fixed points identical for every individual. Some authors adopt instead a sampling procedure and also assume that the choice set may differ across households. A second issue concerns the availability of the alternatives. Most authors assume all the values of hours of work within some range are equally available. At the other extreme, some authors assume only two or three alternatives (for example, nonparticipation, part‐time and full‐time) are available for everyone. Some studies account instead for the fact that not all the hour opportunities are equally available to everyone specifying a probability density function of opportunities for each individual. In this paper we explore by simulation the implications of (i) the procedure used to build the choice set (fixed alternatives versus sampled alternatives); (ii) accounting or not accounting for a different availability of alternatives. The results of the evaluation performed in this paper show that the way the choice set is represented has little impact on the fitting of observed values, but a more significant and important impact on the out‐of‐sample prediction performance. Thus, the treatment of the choice sets might have a crucial effect on the result of policy evaluations.