Luojia Hu

First name
Luojia
Last name
Hu
Author
Abstract

This paper proposes a method for estimating a censored panel data model with a lagged
latent dependent variable and individual-specific fixed effects. The main insight is to trim
observations in such a way that a certain symmetry, which was destroyed by censoring, is
restored. Based on the restored symmetry, orthogonality conditions are constructed and GMM
estimation is implemented. The estimation method is used to study earnings dynamics, using
matched data from the Current Population Survey and Social Security Administration (CPS-
SSA) Earnings Record for a sample of men who were born in 1930-39 and living in the South
dining the period of 1957-73. The SSA earnings are top-coded at the maximum social security
taxable level. Although linear GMM estimation yields no difference in earnings dynamics by
race, the earnings process for white men appears to be more persistent than that for black men
(conditional on individual heterogeneity) after censoring is taken into account.

Year of Publication
2000
Number
435
Date Published
03/2000
Publication Language
eng
Citation Key
Econometrica , Vol. 70, No. 6 (Nov., 2002)
Hu, L. . (2000). Estimating a Censored Dynamic Panel Data Model with an Application to Earnings Dynamics. Retrieved from http://arks.princeton.edu/ark:/88435/dsp017w62f821k (Original work published March 2000)
Working Papers
Author
Abstract

The firm-specific human capital theory implies that large firms prefer to hire younger workers
because they invest more in workers than small firms do and because those investments are fixed
costs. In this paper, I use data from the Benefits Supplement to the Current Population Survey
(CPS) to demonstrate that large firms indeed hire younger workers than small firms, especially for
white-collar occupations. I present a simple model of firm cost minimization within an employee
search framework, which is consistent with large firms’ propensity to hire younger workers, and has
additional testable implications regarding large firms’ compensation structures. First, since young
workers are more valuable to large firms than to small firms, large firms ofier higher starting wages
to attract them. This implies flatter starting wage—age profiles among the new hires in large firms.
Second, since large firms invest more in workers, they continue to pay higher wages to retain the
trained employees. This implies steeper wage-tenure profiles in large firms. Both predictions are
borne out by the CPS data. Most strikingly, for the newly hired white-collar workers, not only are
the starting wage-age profiles flatter in large finns, but also the size-wage premium disappears for
workers hired at age 35 or older.
Furthermore, by exploiting cost variations in dimensions other than firm size, such as occupation
and industry, this model has additional testable implications. More specifically, an extension of
the simple model would imply that, for high training occupations, workers displaced at older ages
suffer greater wage losses than younger workers because they have a harder time finding a new good
job that requires high investments. But there should be no systematic difference in wage loss by
age for occupations that require little training. This prediction is supported by the data from the
Displaced Worker Surveys. Finally, limited evidence from the BLS Survey of Employer Provided
Training 1995 and the CPS suggests that industries that train more also appear to hire younger
workers.

Year of Publication
2000
Number
436
Date Published
03/2000
Publication Language
eng
Citation Key
Econometrica, Vol. 70, No. 6, November, 2002
Hu, L. . (2000). Who Gets Good Jobs? The Hiring Decisions and Compensation Structures of Large Firms. Retrieved from http://arks.princeton.edu/ark:/88435/dsp01pr76f3411 (Original work published March 2000)
Working Papers
Abstract

We propose a new econometric estimation method for analyzing the probability of leaving unemployment
using uncompleted spells from repeated cross-section data, which can be especially
useful when panel data are not available. The proposed method-of-moments-based estimator
has two important features: (1) it estimates the exit probability at the individual level and (2)
it does not rely on the stationarity assumption of the inflow composition. We illustrate and
gauge the performance of the proposed estimator using the Spanish Labor Force Survey data,
and analyze the changes in distribution of unemployment between the 1980s and 1990s during
a period of labor market reform. We find that the relative probability of leaving unemployment
of the short-term unemployed versus the long-term unemployed becomes significantly higher in
the 1990s.

Year of Publication
2003
Number
475
Date Published
05/2003
Publication Language
eng
Citation Key
8357
Guell, M. ., & Hu, L. . (2003). Estimating the Probability of Leaving Unemployment Using Uncompleted Spells from Repeated Cross-section Data. Retrieved from http://arks.princeton.edu/ark:/88435/dsp019p290934d (Original work published May 2003)
Working Papers