A semi-parametric estimator for censored selection models with endogeneity

Myoung-jae Lee, Francis Vella

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

We propose a semi-parametric least-squares estimator for a censored-selection (type 3 tobit) model under the mean independence of the outcome equation error u from the regressors given the selection indicator and its error term ε. This assumption is relatively weak in comparison to alternative estimators for this model and allows certain unknown forms of heteroskedasticity, an asymmetric error distribution, and an arbitrary relationship between the u and ε. The estimator requires only one-dimensional smoothing on the estimate of ε. We generalize the estimator to allow for an endogenous regressor whose equation contains an error ω related to u and discuss how this latter procedure can be adapted to two-wave panel censored-selection models with double selection indicators. In general, each additional endogeneity problem can be controlled for with an extra dimensional smoothing on the residual for the "endogeneity-origin" error term. Our proposed estimators are N-consistent and asymptotically normal. An empirical example based on estimating a wage equation for Australian female youth is provided to illustrate our approach.

Original languageEnglish
Pages (from-to)235-252
Number of pages18
JournalJournal of Econometrics
Volume130
Issue number2
DOIs
Publication statusPublished - 2006 Feb 1
Externally publishedYes

Fingerprint

Endogeneity
Selection Model
Estimator
Error term
Smoothing
Tobit Model
Heteroskedasticity
Wages
Least Squares Estimator
Unknown
Generalise
Selection model
Semiparametric estimators
Model Selection
Alternatives
Arbitrary
Estimate
Equations

Keywords

  • Censored model
  • Panel data
  • Selection problem
  • Type 3 tobit

ASJC Scopus subject areas

  • Economics and Econometrics
  • Finance
  • Statistics and Probability

Cite this

A semi-parametric estimator for censored selection models with endogeneity. / Lee, Myoung-jae; Vella, Francis.

In: Journal of Econometrics, Vol. 130, No. 2, 01.02.2006, p. 235-252.

Research output: Contribution to journalArticle

@article{f5a3e4c83f354d4e82890d549ef19b60,
title = "A semi-parametric estimator for censored selection models with endogeneity",
abstract = "We propose a semi-parametric least-squares estimator for a censored-selection (type 3 tobit) model under the mean independence of the outcome equation error u from the regressors given the selection indicator and its error term ε. This assumption is relatively weak in comparison to alternative estimators for this model and allows certain unknown forms of heteroskedasticity, an asymmetric error distribution, and an arbitrary relationship between the u and ε. The estimator requires only one-dimensional smoothing on the estimate of ε. We generalize the estimator to allow for an endogenous regressor whose equation contains an error ω related to u and discuss how this latter procedure can be adapted to two-wave panel censored-selection models with double selection indicators. In general, each additional endogeneity problem can be controlled for with an extra dimensional smoothing on the residual for the {"}endogeneity-origin{"} error term. Our proposed estimators are N-consistent and asymptotically normal. An empirical example based on estimating a wage equation for Australian female youth is provided to illustrate our approach.",
keywords = "Censored model, Panel data, Selection problem, Type 3 tobit",
author = "Myoung-jae Lee and Francis Vella",
year = "2006",
month = "2",
day = "1",
doi = "10.1016/j.jeconom.2004.11.001",
language = "English",
volume = "130",
pages = "235--252",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier BV",
number = "2",

}

TY - JOUR

T1 - A semi-parametric estimator for censored selection models with endogeneity

AU - Lee, Myoung-jae

AU - Vella, Francis

PY - 2006/2/1

Y1 - 2006/2/1

N2 - We propose a semi-parametric least-squares estimator for a censored-selection (type 3 tobit) model under the mean independence of the outcome equation error u from the regressors given the selection indicator and its error term ε. This assumption is relatively weak in comparison to alternative estimators for this model and allows certain unknown forms of heteroskedasticity, an asymmetric error distribution, and an arbitrary relationship between the u and ε. The estimator requires only one-dimensional smoothing on the estimate of ε. We generalize the estimator to allow for an endogenous regressor whose equation contains an error ω related to u and discuss how this latter procedure can be adapted to two-wave panel censored-selection models with double selection indicators. In general, each additional endogeneity problem can be controlled for with an extra dimensional smoothing on the residual for the "endogeneity-origin" error term. Our proposed estimators are N-consistent and asymptotically normal. An empirical example based on estimating a wage equation for Australian female youth is provided to illustrate our approach.

AB - We propose a semi-parametric least-squares estimator for a censored-selection (type 3 tobit) model under the mean independence of the outcome equation error u from the regressors given the selection indicator and its error term ε. This assumption is relatively weak in comparison to alternative estimators for this model and allows certain unknown forms of heteroskedasticity, an asymmetric error distribution, and an arbitrary relationship between the u and ε. The estimator requires only one-dimensional smoothing on the estimate of ε. We generalize the estimator to allow for an endogenous regressor whose equation contains an error ω related to u and discuss how this latter procedure can be adapted to two-wave panel censored-selection models with double selection indicators. In general, each additional endogeneity problem can be controlled for with an extra dimensional smoothing on the residual for the "endogeneity-origin" error term. Our proposed estimators are N-consistent and asymptotically normal. An empirical example based on estimating a wage equation for Australian female youth is provided to illustrate our approach.

KW - Censored model

KW - Panel data

KW - Selection problem

KW - Type 3 tobit

UR - http://www.scopus.com/inward/record.url?scp=31344470214&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=31344470214&partnerID=8YFLogxK

U2 - 10.1016/j.jeconom.2004.11.001

DO - 10.1016/j.jeconom.2004.11.001

M3 - Article

AN - SCOPUS:31344470214

VL - 130

SP - 235

EP - 252

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 2

ER -