A Note on Consistency of Heckman-Type Two-Step Estimators for the Multivariate Sample-Selection Model

28 Pages Posted: 8 May 2006

See all articles by Harald Tauchmann

Harald Tauchmann

Rhine-Westphalia Institute for Economic Research (RWI-Essen)

Date Written: April 2006

Abstract

This analysis shows that multivariate generalizations to the classical Heckman (1976 and 1979) two-step estimator that account for cross-equation correlation and use the inverse Mills ratio as a correction-term are consistent only if certain restrictions apply to the true error-covariance structure. We derive an alternative class of generalizations to the classical Heckman two-step approach that conditions on the entire selection pattern rather than the selection of particular equations and, therefore, uses modified correction-terms. This class of estimators is shown to be consistent. In addition, Monte-Carlo results illustrate that these estimators display a smaller mean square prediction error.

Keywords: Multivariate sample-selection model, censored system of equations

JEL Classification: C15, C34, C51

Suggested Citation

Tauchmann, Harald, A Note on Consistency of Heckman-Type Two-Step Estimators for the Multivariate Sample-Selection Model (April 2006). RWI: Discussion Paper No. 40, Available at SSRN: https://ssrn.com/abstract=900079 or http://dx.doi.org/10.2139/ssrn.900079

Harald Tauchmann (Contact Author)

Rhine-Westphalia Institute for Economic Research (RWI-Essen) ( email )

Hohenzollernstr. 1-3
45128 Essen
Germany