SIQI WEI

This paper studies choice models with piecewise smooth objective functions. By introducing well-defined latent variables derived from regional components (auxiliary functions), we provide conditions under which the choice model can be transformed into a reduced form resembling Tobit-like models, with the introduced latent vari- ables as potential outcomes. The potential outcome framework not only serves as an alternative solution method for the choice model, but also facilitates the implemen- tation of the stochastic Expectation-Maximization (SEM) algorithm to obtain MLE. We illustrate the framework using two simple examples: 1) responses to tax and transfers, and 2) the (𝑆, 𝑠) model. We further empirically estimate a joint retirement decision model among European couples based on the interdependent duration model in Honoré and de Paula (2018), applying the proposed solution and estimation methods. The results provide empirical evidence of complementarity between spouses in their transition out of the labor force in Europe.

This paper begins with the observation that many older workers move to "bridge" jobs with lower wages and fewer working hours before exiting the labor force for good. To explain this smooth transition to full retirement, I propose a nonlinear aging-related shock — mismatch shock, which mismatches workers with their existing job and triggers job leaves. I develop an empirical framework of employment and job transitions jointly with stochastic wage and hour processes, which allows us to separate health risks, individual-specific productivity risks, firm-specific mismatch risks, quality of outside offers, and job destruction risks faced by older workers. The model is estimated with a sample of male individuals aged 51 to 70 in the US Health and Retirement Study applying a novel parameter-expanded stochastic EM algorithm. The paper finds that mismatch shocks play an important role in explaining the reduction in wages and hours for movers. Shutting down mismatch shocks implies that the mean wage drop of movers is reduced by around 55%, and the variance of wage changes is reduced by 17% − 28%, depending on age groups. Furthermore, I calculate the welfare cost of risks and quantify how much individuals value the possibility of a flexible transition to full retirement by constructing a utility-based structural model of consumption, employment and job movements where agents face the same risks as in the empirical model. The model is estimated using a novel simulation-based algorithm that exploits the connection to the empirical model and the estimates from the empirical model. The results show that the median cost of mismatch risks amounts to a reduction in consumption flow by 5.3%−7.1% depending on the education group. Banning job changes and re-entry causes a welfare loss equivalent to a consumption drop of 12% − 14%.

This paper presents new estimation algorithms for three types of dynamic panel data models with latent variables: factor models, discrete choice models, and persistent-transitory quantile processes. The new methods combine the parameter expansion (PX) ideas in Liu et al. (1998) with the stochastic expectation-maximization (SEM) algorithm in likelihood and moment-based contexts. The goal is to facilitate convergence in models with a large space of latent variables by improving algorithmic efficiency. This is achieved by specifying expanded models within the M step. Effectively, we are proposing new estimators for the pseudo-data within iterations that take into account the fact that the model of interest is misspecified for draws based on parameter values far from the truth. We establish the asymptotic equivalence of the likelihood-based PX-SEM to an alternative SEM algorithm with a smaller expected fraction of missing information compared to the standard SEM based on the original model, implying a faster global convergence rate. Finally, in simulations we show that the new algorithms significantly improve the convergence speed relative to standard SEM algorithms, sometimes dramatically so, by reducing the total computing time from hours to a few minutes.

In this paper we use administrative data from the social security to study income dynamics and income risk inequality in Spain between 2005 and 2018. We construct individual measures of income risk as functions of past employment history, income, and demographics. Focusing on males, we document that income risk is highly unequal in Spain: more than half of the economy has close to perfect predictability of their income, while some face considerable uncertainty. Income risk is inversely related to income and age, and income risk inequality increases markedly in the recession. These findings are robust to a variety of specifications, including using neural networks for prediction and allowing for individual unobserved heterogeneity.