Estimation of sample selection bias models
- 1 January 1996
- journal article
- research article
- Published by Taylor & Francis in Econometric Reviews
- Vol. 15 (4) , 387-400
- https://doi.org/10.1080/07474939608800363
Abstract
Econometric models with sample selection biases are widely used in various fields of economics, such as labor economics. The Maximum Likelihood Estimator (MLE) is seldom used to estimate models because of computational difficulty, while Heckman's two-step estimator is widely used to estimate these models. However, Heckman's two-step estimator sometimes performs poorly. In this paper, methods of calculating the MLE are analysed, and finite sample properties of the MLE and Heckman's two-step estimator are compared using Monte Carlo experiments and empirical examples.Keywords
This publication has 13 references indexed in Scilit:
- Estimation of sample selection bias models by the maximum likelihood estimator and Heckman's two-step estimatorEconomics Letters, 1994
- The Sensitivity of an Empirical Model of Married Women's Hours of Work to Economic and Statistical AssumptionsEconometrica, 1987
- A Monte Carlo comparison of estimators for censored regression modelsJournal of Econometrics, 1984
- Efficiency of the two-step estimator for models with endogenous sample selectionJournal of Econometrics, 1984
- Distributional Tests for Selectivity Bias and a More Robust Likelihood EstimatorInternational Economic Review, 1982
- Approximating a Truncated Normal Regression with the Method of MomentsEconometrica, 1980
- Sample Selectivity and the Estimation of Labor Supply FunctionsInternational Economic Review, 1980
- A Heteroskedasticity-Consistent Covariance Matrix Estimator and a Direct Test for HeteroskedasticityEconometrica, 1980
- Sample Selection Bias as a Specification ErrorEconometrica, 1979
- Shadow Prices, Market Wages, and Labor SupplyEconometrica, 1974