This paper addresses estimation of an outcome characterized by mass at zero, significant skewness, and heteroscedasticity. Unlike other approaches suggested recently that require retransformations or arbitrary assumptions about error distributions, our estimation strategy uses sequences of...

While individual smoking behavior persists over time, it is unknown whether this repeated behavior is due to addiction or individual propensities to smoke. To address this issue, we develop a dynamic empirical model of smoking decisions which explicitly accounts for the impact of previous...

We estimate the impact of employer-provided retiree health insurance on the rate at which men aged 51-62 enter and exit the labor force and switch jobs. The models estimated are an approximation of the employment decision rules implied by a dynamic stochastic model of employment behavior of...

In this study we quantify the life-cycle effects of human and health capital on the wage distribution of females, with a focus on health measured by body mass. We use NLSY79 data on women followed annually up to twenty years during the time of their lives when average annual weight gain is...

Individual smoking behavior persists over time, but is this repeated behavior attributed to past use or individual heterogeneity? Using longitudinal data on teens from all 50 United States from 1988 to 1992, we find a significant causal role for endogenous past cigarette consumption even after...

Prescription drug coverage creates a change in medical care consumption, beyond standard moral hazard, arising both from the differential cost-sharing and the relative effectiveness of different types of care. We model the dynamic supplemental health insurance decisions of Medicare...