Empirical analyses of retirement typically assume a single form of retirement. In this paper, I consider the determinants of retirement in a competing risks model which allows for full and partial retirement. Simulation results indicate that the large increase in Social Security benefits in the...

Empirical analyses of retirement typically assume a single form of retirement. In this paper, I consider the determinants of retirement in a competing risks model which allows for full and partial retirement. Simulation results indicate that the large increase in Social Security benefits in the...

This paper outlines a two-stage technique for estimation and inference in probit models with structural group effects. The structural group specification belongs to a broader class of random components models. In particular, individuals in a given group share a common component in the...

There exist sizeable differences in the incidence and duration of welfare spells across ethnic groups, and these differences tend to persist across generations. Using the National Longitudinal Surveys of Youth, we find that children raised in welfare households are themselves more likely to...

This paper outlines a two-stage technique for estimation and inference in probit models with structural group effects. The structural group specification belongs to a broader class of random components models. In particular, individuals in a given group share a common component in the...

There exist sizeable differences in the incidence and duration of welfare spells across ethnic groups, and these differences tend to persist across generations. Using the National Longitudinal Surveys of Youth, we find that children raised in welfare households are themselves more likely to...

Recent work by Schennach (2005) has opened the way to a Bayesian treatment of quantile regression. Her method, called Bayesian exponentially tilted empirical likelihood (BETEL), provides a likelihood for data y subject only to a set of m moment conditions of the form Eg(y, θ) = 0 where θ is a...