Test statistics and critical values in selectivity models

R C  Hill; L C  Adkins; K A  Bender

doi:10.1016/S0731-9053(03)17004-1

Test statistics and critical values in selectivity models

R C Hill, L C Adkins, K A Bender

Economics

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

16 Citations (Scopus)

Abstract

The Heckman two-step estimator (Heckit) for the selectivity model is widely applied in Economics and other social sciences. In this model a non-zero outcome variable is observed only if a latent variable is positive. The asymptotic covariance matrix for a two-step estimation procedure must account for the estimation error introduced in the first stage. We examine the finite sample size of tests based on alternative covariance matrix estimators. We do so by using Monte Carlo experiments to evaluate bootstrap generated critical values and critical values based on asymptotic theory.

Original language	English
Title of host publication	Maximum Likelihood Estimation of Misspecified Models
Subtitle of host publication	Twenty years later
Editors	TB Fomby, RC Hill
Place of Publication	Amsterdam
Publisher	JAI-ELSEVIER SCI BV
Pages	75-105
Number of pages	31
Volume	17
ISBN (Print)	0-7623-1075-8
DOIs	https://doi.org/10.1016/S0731-9053(03)17004-1
Publication status	Published - 2003

Keywords

sample-selection
specification error
bias
estimators
time

Access to Document

10.1016/S0731-9053(03)17004-1

Cite this

@inproceedings{760c925754f44316ab14ecc3e05854a9,

title = "Test statistics and critical values in selectivity models",

abstract = "The Heckman two-step estimator (Heckit) for the selectivity model is widely applied in Economics and other social sciences. In this model a non-zero outcome variable is observed only if a latent variable is positive. The asymptotic covariance matrix for a two-step estimation procedure must account for the estimation error introduced in the first stage. We examine the finite sample size of tests based on alternative covariance matrix estimators. We do so by using Monte Carlo experiments to evaluate bootstrap generated critical values and critical values based on asymptotic theory.",

keywords = "sample-selection, specification error, bias, estimators, time",

author = "Hill, {R C} and Adkins, {L C} and Bender, {K A}",

year = "2003",

doi = "10.1016/S0731-9053(03)17004-1",

language = "English",

isbn = "0-7623-1075-8",

volume = "17",

pages = "75--105",

editor = "TB Fomby and RC Hill",

booktitle = "Maximum Likelihood Estimation of Misspecified Models",

publisher = "JAI-ELSEVIER SCI BV",

}

TY - GEN

T1 - Test statistics and critical values in selectivity models

AU - Hill, R C

AU - Adkins, L C

AU - Bender, K A

PY - 2003

Y1 - 2003

N2 - The Heckman two-step estimator (Heckit) for the selectivity model is widely applied in Economics and other social sciences. In this model a non-zero outcome variable is observed only if a latent variable is positive. The asymptotic covariance matrix for a two-step estimation procedure must account for the estimation error introduced in the first stage. We examine the finite sample size of tests based on alternative covariance matrix estimators. We do so by using Monte Carlo experiments to evaluate bootstrap generated critical values and critical values based on asymptotic theory.

AB - The Heckman two-step estimator (Heckit) for the selectivity model is widely applied in Economics and other social sciences. In this model a non-zero outcome variable is observed only if a latent variable is positive. The asymptotic covariance matrix for a two-step estimation procedure must account for the estimation error introduced in the first stage. We examine the finite sample size of tests based on alternative covariance matrix estimators. We do so by using Monte Carlo experiments to evaluate bootstrap generated critical values and critical values based on asymptotic theory.

KW - sample-selection

KW - specification error

KW - bias

KW - estimators

KW - time

U2 - 10.1016/S0731-9053(03)17004-1

DO - 10.1016/S0731-9053(03)17004-1

M3 - Published conference contribution

SN - 0-7623-1075-8

VL - 17

SP - 75

EP - 105

BT - Maximum Likelihood Estimation of Misspecified Models

A2 - Fomby, TB

A2 - Hill, RC

PB - JAI-ELSEVIER SCI BV

CY - Amsterdam

ER -

Test statistics and critical values in selectivity models

Abstract

Keywords

Access to Document

Fingerprint

Cite this