We modify the Additively Non-ignorable (AN) model of Hirano et. al. (2001) so that it is suitable for data collection efforts that have a short panel component. Our modification yields a convenient semi-parametric bias correction framework for handling endogenous attrition and substitution...

We modify the Additively Non-ignorable (AN) model of Hirano et. al. (2001) so that it is suitable for data collection efforts that have a short panel component. Our modification yields a convenient semi-parametric bias correction framework for handling endogenous attrition and substitution...

We study the aggregate labor force participation behavior of women over a 25-year period in Turkey using a synthetic panel approach. In our decomposition of age, year, and cohort effects, we use three APC models that have received close scrutiny of the demography community. We rely on...

We study the aggregate labor force participation behavior of women over a 25-year period in Turkey using a synthetic panel approach. In our decomposition of age, year, and cohort effects, we use three APC models that have received close scrutiny of the demography community. We rely on...

estimated in the context of a three-state labor market application. Futher, strict bounds on the estimated probabilities are calculated using Manski’s bounds approach. Empirical findings confirm that attrition is non-ignorable, and neither MAR nor HW adequately model it.

This paper studies how firing costs affect the productivity of knowledge workers. We develop a holdup model in which workers are essential to knowledge transfer between firms and show that if the worker's knowledge stock is sufficiently transferable to competing firms, an increase in firing...

This paper explores, both theoretically and empirically, how firing costs affect worker productivity and turnover. We develop a model in which workers are essential to knowledge transfer between firms and worker effort is firm-specific in the sense that a worker can be fired before reaping the...