Report · 1977 · Open access

Sample Selection Bias As a Specification Error (with an Application to the Estimation of Labor Supply Functions)

James J. Heckman

National Bureau of Economic Research · Published 1 March 1977 · DOI 10.3386/w0172

Free PDFCite this paper

In brief

“Sample Selection Bias As a Specification Error (with an Application to the Estimation of Labor Supply Functions)” is a 1977 report by James J. Heckman, published in National Bureau of Economic Research. OpenAlex counts 422 citations as of 16 November 2026. It is open access: the full text is free to read at National Bureau of Economic Research.

Citations
422
Most cited in
2019 (50)
References
15
Authors
1

Abstract

Moreover, in each case, if it were possible to obtain the missing wage data for either the treatment or nontreatment population, it would be possible to utilize simple regression techniques to estimate the parameters of population functions.Simple comparisons between pre and post treatment wages would yield unbiased estimates of the economic benefits of the treatment.Sample selection bias may also arise as a direct consequence of actions taken by the analyst.In studies of panel data, it is common to require that "intact" observations be employed.For example, in analyses of the time series of the labor supply of married women, stability of the family unit is often required.foran observation sequence to be analyzed.The effect of such criteria operates in precisely the same fashion as self selection: fitted functions confound behavioral functions with sample selection functions.It is fair to say that most competent analysts have been aware of the possibility of both sources of selection bias.It is also fair to say that the accepted econometric practice has been to ignore the problem in making parameter estimates but to verbally qualify the estimates in light of possible selection biases.Recent work in econometrics has attempted to improve on previous work by making specific assumptions about the source of selection bias.In particular, this work assumes that both the missing data and the available data are drawn from a common probability distribution, typically assumed to be a normal law.Except for work by Amemiya (1973) and Gronau (1974), the authors of /these studies rely on maximum likelihood estimators to produce parameter estimates free of selection bias.In this paper, I present a simple characterization of the sample also selection bias problem that is/applicable to the conceptually distinct

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Heckman, J. J. (1977). Sample Selection Bias As a Specification Error (with an Application to the Estimation of Labor Supply Functions). National Bureau of Economic Research. https://doi.org/10.3386/w0172

MLA 9

Heckman, James J. “Sample Selection Bias As a Specification Error (with an Application to the Estimation of Labor Supply Functions).” National Bureau of Economic Research, 1977. https://doi.org/10.3386/w0172.

Chicago

Heckman, James J. 1977. “Sample Selection Bias As a Specification Error (with an Application to the Estimation of Labor Supply Functions).” National Bureau of Economic Research. https://doi.org/10.3386/w0172.

Harvard

Heckman, J. J. (1977) ‘Sample Selection Bias As a Specification Error (with an Application to the Estimation of Labor Supply Functions)’, National Bureau of Economic Research. doi:10.3386/w0172.

IEEE

J. J. Heckman, “Sample Selection Bias As a Specification Error (with an Application to the Estimation of Labor Supply Functions),” National Bureau of Economic Research, 1977, doi: 10.3386/w0172.

BibTeX

@article{heckman1977sample,
  title     = {{Sample Selection Bias As a Specification Error (with an Application to the Estimation of Labor Supply Functions)}},
  author    = {Heckman, James J.},
  journal   = {National Bureau of Economic Research},
  year      = {1977},
  doi       = {10.3386/w0172},
  url       = {https://doi.org/10.3386/w0172}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
20172222
20184646
20195050
20204040
20212424
20221717
20231313
20241414
202588
202655

Topic and keywords

Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques

  • sample selection bias
  • model misspecification
  • labor supply function
  • self-selection
  • missing data
  • panel data
  • married women's labor supply
  • econometric estimation

Work with this paper

Most-cited papers in Mathematics

All highly cited Mathematics papers

Questions about this paper

How do I cite this paper in APA style?

Heckman, J. J. (1977). Sample Selection Bias As a Specification Error (with an Application to the Estimation of Labor Supply Functions). National Bureau of Economic Research. https://doi.org/10.3386/w0172

How many times has this paper been cited?

422 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at National Bureau of Economic Research.

Who wrote this paper?

James J. Heckman.

What is the DOI of this paper?

10.3386/w0172. The permanent link is https://doi.org/10.3386/w0172.

Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.