The Heckman correction (the two-stage method, Heckman's lambda or the Heckit method) is any of a number of related statistical methods developed by James Heckman at the University of Chicago from 1976 to 1979 which allow the researcher to correct for selection bias. Selection bias problems are endemic to applied econometric problems, which make Heckman’s original technique, and subsequent refinements by both himself and others, indispensable to applied econometricians. Heckman received the Economics Nobel Prize in 2000 for his work in this field.
Statistical analyses based on non-randomly selected samples can lead to erroneous conclusions. The Heckman correction, a two-step statistical approach, offers a means of correcting for non-randomly selected samples.
Heckman discussed bias from using nonrandom selected samples to estimate behavioral relationships as a specification error. He suggests a two-stage estimation method to correct the bias. The correction uses a control function idea and is easy to implement. Heckman’s correction involves a normality assumption, provides a test for sample selection bias and formula for bias corrected model.
Suppose that a researcher wants to estimate the determinants of wage offers, but has access to wage observations for only those who work. Since people who work are selected non-randomly from the population, estimating the determinants of wages from the subpopulation who work may introduce bias. The Heckman correction takes place in two stages.
where D indicates employment (D = 1 if the respondent is employed and D = 0 otherwise), Z is a vector of explanatory variables, is a vector of unknown parameters, and Φ is the cumulative distribution function of the standard normal distribution. Estimation of the model yields results that can be used to predict this employment probability for each individual.
In the second stage, the researcher corrects for self-selection by incorporating a transformation of these predicted individual probabilities as an additional explanatory variable. The wage equation may be specified,
where denotes an underlying wage offer, which is not observed if the respondent does not work. The conditional expectation of wages given the person works is then
where ρ is the correlation between unobserved determinants of propensity to work and unobserved determinants of wage offers u, σ u is the standard deviation of , and is the inverse Mills ratio evaluated at . This equation demonstrates Heckman's insight that sample selection can be viewed as a form of omitted-variables bias, as conditional on both X and on it is as if the sample is randomly selected. The wage equation can be estimated by replacing with Probit estimates from the first stage, constructing the term, and including it as an additional explanatory variable in linear regression estimation of the wage equation. Since , the coefficient on can only be zero if , so testing the null that the coefficient on is zero is equivalent to testing for sample selectivity.
Heckman's achievements have generated a large number of empirical applications in economics as well as in other social sciences. The original method has subsequently been generalized, by Heckman and by others.
- The two-step estimator discussed above is a limited information maximum likelihood (LIML) estimator. In asymptotic theory and in finite samples as demonstrated by Monte Carlo simulations, the full information (FIML) estimator exhibits better statistical properties. However, the FIML estimator is more computationally difficult to implement.
- The covariance matrix generated by OLS estimation of the second stage is inconsistent. Correct standard errors and other statistics can be generated from an asymptotic approximation or by resampling, such as through a bootstrap.
- The canonical model assumes the errors are jointly normal. If that assumption fails, the estimator is generally inconsistent and can provide misleading inference in small samples. Semiparametric and other robust alternatives can be used in such cases.
- The model obtains formal identification from the normality assumption when the same covariates appear in the selection equation and the equation of interest, but identification will be tenuous unless there are many observations in the tails where there is substantial nonlinearity in the inverse Mills ratio. Generally, an exclusion restriction is required to generate credible estimates: there must be at least one variable which appears with a non-zero coefficient in the selection equation but does not appear in the equation of interest, essentially an instrument. If no such variable is available, it may be difficult to correct for sampling selectivity.
Implementations in statistics packages
- R: Heckman-type procedures are available as part of the
- Stata: the command
heckmanprovides the Heckman selection model.
- Heckit: 'Heck-' from Heckman and '-it' as in probit, tobit, and logit.
- Heckman, J. (1979). "Sample selection bias as a specification error". Econometrica. 47 (1): 153–61. doi:10.2307/1912352. JSTOR 1912352.
- Gronau, Reuben (1974). "Wage Comparisons—A Selectivity Bias". Journal of Political Economy. 82 (6): 1119–1143. doi:10.1086/260267. JSTOR 1830664.
- Lewis, H. Gregg (1974). "Comments on Selectivity Biases in Wage Comparisons". Journal of Political Economy. 82 (6): 1145–1155. doi:10.1086/260268. JSTOR 1830665.
- Lee, Lung-Fei (2001). "Self-selection". In Baltagi, B. A Companion to Theoretical Econometrics. Oxford: Blackwell. doi:10.1002/9780470996249.ch19.
- Puhani, P. (2000). "The Heckman Correction for sample selection and its critique". Journal of Economic Surveys. 14 (1): 53–68. doi:10.1111/1467-6419.00104.
- Cameron, A. Colin; Trivedi, Pravin K. (2005). "Sequential Two-Step m-Estimation". Microeconometrics: Methods and Applications. New York: Cambridge University Press. pp. 200–202. ISBN 0-521-84805-9.
- Goldberger, A. (1983). "Abnormal Selection Bias". In Karlin, Samuel; Amemiya, Takeshi; Goodman, Leo. Studies in Econometrics, Time Series, and Multivariate Statistics. New York: Academic Press. pp. 67–84. ISBN 0-12-398750-4.
- Newey, Whitney; Powell, J.; Walker, James R. (1990). "Semiparametric Estimation of Selection Models: Some Empirical Results". American Economic Review. 80 (2): 324–28.
- Toomet, O.; Henningsen, A. (2008). "Sample Selection Models in R: Package sampleSelection". Journal of Statistical Software. 27 (7): 1–23. doi:10.18637/jss.v027.i07.
- "sampleSelection: Sample Selection Models". R Project.
- "heckman — Heckman selection model" (PDF). Stata Manual.
- Cameron, A. Colin; Trivedi, Pravin K. (2010). Microeconometrics Using Stata (Revised ed.). College Station: Stata Press. pp. 556–562. ISBN 978-1-59718-073-3.
- Arminger, Gerhard (1996). "The Analysis of Panel Data with Nonmetric Variables: Probit Models and a Heckman Correction for Selectivity Bias". In Engel, Uwe; Reinecke, Jost. Analysis of Change: Advanced Techniques in Panel Data Analysis. Berlin: Walter de Gruyter. pp. 61–85. ISBN 3-11-014936-2.
- Cameron, A. Colin; Trivedi, Pravin K. (2005). "Sample Selection Models". Microeconometrics: Methods and Applications. New York: Cambridge University Press. pp. 546–53. ISBN 0-521-84805-9.
- Davidson, Russell; MacKinnon, James G. (2004). "Sample Selectivity". Econometric Theory and Methods. New York: Oxford University Press. pp. 486–89. ISBN 0-19-512372-7.
- Greene, William H. (2012). "Incidental Truncation and Sample Selection". Econometric Analysis (Seventh ed.). Boston: Pearson. pp. 912–27. ISBN 978-0-273-75356-8.
- Verbeek, Marno (2004). A Guide to Modern Econometrics (Second ed.). New York: Wiley. pp. 227–232. ISBN 0-470-85773-0.
- Wooldridge, Jeffrey M. (2002). Econometric Analysis of Cross Section and Panel Data. Cambridge: MIT Press. pp. 562–566. ISBN 0-262-23219-7.