Work experience as a source of specification error in earnings models: Implications for gender wage decompositions

Tracy L. Regan, Ronald L Oaxaca

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

This paper models the bias from using potential vs actual experience in log wage models. The nature of the problem is best viewed as specification error as opposed to classical errors-in-variables. We correct for the discrepancy between potential and actual work experience and create a predicted measure of work experience. We use the 1979 National Longitudinal Survey of Youth and the Panel Study of Income Dynamics and extend our findings to the Integrated Public Use Microdata Sample. Our results suggest that potential experience biases the effects of schooling and the rates of return to labor market experience. Using such a measure in earnings models underestimates the explained portion of the male-female wage gap. We are able to separately identify the decomposition biases associated with incorrect experience measures and biased parameter estimates.

Original languageEnglish (US)
Pages (from-to)463-499
Number of pages37
JournalJournal of Population Economics
Volume22
Issue number2
DOIs
StatePublished - Apr 2009

Fingerprint

wage
gender
experience
trend
Wage decomposition
Work experience
Specification error
labor market
income
Income
Rate of return
Panel study
Decomposition
Integrated
Wages
Errors in variables
Wage gap
Micro data
Labour market
Schooling

Keywords

  • Decomposition
  • Experience
  • Specification error

ASJC Scopus subject areas

  • Demography
  • Economics and Econometrics

Cite this

Work experience as a source of specification error in earnings models : Implications for gender wage decompositions. / Regan, Tracy L.; Oaxaca, Ronald L.

In: Journal of Population Economics, Vol. 22, No. 2, 04.2009, p. 463-499.

Research output: Contribution to journalArticle

@article{b3a6198ec8d04283948ff9800b327282,
title = "Work experience as a source of specification error in earnings models: Implications for gender wage decompositions",
abstract = "This paper models the bias from using potential vs actual experience in log wage models. The nature of the problem is best viewed as specification error as opposed to classical errors-in-variables. We correct for the discrepancy between potential and actual work experience and create a predicted measure of work experience. We use the 1979 National Longitudinal Survey of Youth and the Panel Study of Income Dynamics and extend our findings to the Integrated Public Use Microdata Sample. Our results suggest that potential experience biases the effects of schooling and the rates of return to labor market experience. Using such a measure in earnings models underestimates the explained portion of the male-female wage gap. We are able to separately identify the decomposition biases associated with incorrect experience measures and biased parameter estimates.",
keywords = "Decomposition, Experience, Specification error",
author = "Regan, {Tracy L.} and Oaxaca, {Ronald L}",
year = "2009",
month = "4",
doi = "10.1007/s00148-007-0180-5",
language = "English (US)",
volume = "22",
pages = "463--499",
journal = "Journal of Population Economics",
issn = "0933-1433",
publisher = "Springer New York",
number = "2",

}

TY - JOUR

T1 - Work experience as a source of specification error in earnings models

T2 - Implications for gender wage decompositions

AU - Regan, Tracy L.

AU - Oaxaca, Ronald L

PY - 2009/4

Y1 - 2009/4

N2 - This paper models the bias from using potential vs actual experience in log wage models. The nature of the problem is best viewed as specification error as opposed to classical errors-in-variables. We correct for the discrepancy between potential and actual work experience and create a predicted measure of work experience. We use the 1979 National Longitudinal Survey of Youth and the Panel Study of Income Dynamics and extend our findings to the Integrated Public Use Microdata Sample. Our results suggest that potential experience biases the effects of schooling and the rates of return to labor market experience. Using such a measure in earnings models underestimates the explained portion of the male-female wage gap. We are able to separately identify the decomposition biases associated with incorrect experience measures and biased parameter estimates.

AB - This paper models the bias from using potential vs actual experience in log wage models. The nature of the problem is best viewed as specification error as opposed to classical errors-in-variables. We correct for the discrepancy between potential and actual work experience and create a predicted measure of work experience. We use the 1979 National Longitudinal Survey of Youth and the Panel Study of Income Dynamics and extend our findings to the Integrated Public Use Microdata Sample. Our results suggest that potential experience biases the effects of schooling and the rates of return to labor market experience. Using such a measure in earnings models underestimates the explained portion of the male-female wage gap. We are able to separately identify the decomposition biases associated with incorrect experience measures and biased parameter estimates.

KW - Decomposition

KW - Experience

KW - Specification error

UR - http://www.scopus.com/inward/record.url?scp=60449100201&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=60449100201&partnerID=8YFLogxK

U2 - 10.1007/s00148-007-0180-5

DO - 10.1007/s00148-007-0180-5

M3 - Article

AN - SCOPUS:60449100201

VL - 22

SP - 463

EP - 499

JO - Journal of Population Economics

JF - Journal of Population Economics

SN - 0933-1433

IS - 2

ER -