The use of historical data has become a standard tool in economics, serving three main purposes: to examine the influence of the past on current economic outcomes; to use unique natural experiments to test modern economic theories; and to use modern economic theories to refine our understanding...

We consider the identification of and inference on a partially linear model, when the outcome of interest and some of the covariates are observed in two different datasets that cannot be linked. This type of data combination problem arises very frequently in empirical microeconomics. Using...

This paper investigates differences in worker turnover characteristics between periods of workforce expansion and contraction in a firm. We derive a Cox proportional hazard model from a simple model of job separation based on the expected surpluses from the firm and its workers. We account for...

Optimal layoff rules in closed form are derived for all workers in a firm that downsizes under uncertainty and faces heterogeneous firing costs. The theoretical model predicts that the firm displaces workers with low firing costs, low expected future productivity growth, and low layoff option...

We construct a general dynamic structural model of two-sided learning between a firm and its workers. We estimate an empirical version of the model using personnel data from Fokker Aircraft that cover the path of layoffs and quits through its bankruptcy. We find that the firm learns about its...