Journal of Economic Perspectives: Vol. 15 No. 4 (Fall 2001)


Quick Tools:

Print Article Summary
Export Citation
Sign up for Email Alerts Follow us on Twitter


JEP - All Issues

Semiparametric Censored Regression Models

Article Citation

Chay, Kenneth Y., and James L. Powell. 2001. "Semiparametric Censored Regression Models." Journal of Economic Perspectives, 15(4): 29-42.

DOI: 10.1257/jep.15.4.29


When data are censored, ordinary least squares regression can provide biased coefficient estimates. Maximum likelihood approaches to this problem are valid only if the error distribution is correctly specified, which can be problematic in practice. We review several semiparametric estimators for the censored regression model that do not require parameterization of the error distribution. These estimators are used to examine changes in black-white earnings inequality during the 1960s based on censored tax records. The results show that there was significant earnings convergence among black and white men in the American South after the passage of the 1964 Civil Rights Act.

Article Full-Text Access

Full-text Article (Complimentary)


Chay, Kenneth Y. (U CA, Berkeley)
Powell, James L. (U CA, Berkeley)

JEL Classifications

C24: Single Equation Models; Single Variables: Truncated and Censored Models
J31: Wage Level and Structure; Wage Differentials
J16: Economics of Gender; Non-labor Discrimination


View Comments on This Article (0) | Login to post a comment

Journal of Economic Perspectives

Quick Tools:

Sign up for Email Alerts

Follow us on Twitter

Subscription Information
(Institutional Administrator Access)


JEP - All Issues

Virtual Field Journals

AEA Member Login:

AEAweb | AEA Journals | Contact Us