Match Bias in Wage Gap Estimates Due to Earnings Imputation

Hirsch, Barry T.; Schumacher, Edward J.

doi:10.1086/383112

Cited by 233 publications

(239 citation statements)

References 28 publications

Supporting

Mentioning

227

Contrasting

Unclassified

Order By: Relevance

“…Other work Horowitz 1998, 2002) has focused on identi…cation conditions when data are missing, but does not directly address the issue of using imputations. Hirsch and Schumacher (2004), whose work we extend, show that coe¢ cient bias resulting from imputation of a dependent variable (earnings) can be of …rst order importance.…”

Section: Introductionmentioning

confidence: 69%

“…The proportion of imputed earners was approximately 15% from 1979-1993, increased as a result of CPS revisions in 1994, and has risen in recent years to almost 30% (Hirsch and Schumacher 2004, Table 2). For a variety of reasons, the Census and the Bureau of Labor Statistics (BLS) choose to include both earnings respondents and nonrespondents in published tabulations of earnings and other outcomes of interest.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Match Bias from Earnings Imputation in the Current Population Survey: The Case of Imperfect Matching

Bollinger

Hirsch

2006

Journal of Labor Economics

Self Cite

148

158

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Terms of use: Documents in Match Bias from Earnings Imputation in the Current Population Survey: The Case of Imperfect MatchingChristopher R. Bollinger Barry T. Hirsch D I S C U S S I O N P A P E R S E R I E S ABSTRACT Match Bias from Earnings Imputation in the CurrentPopulation Survey: The Case of Imperfect Matching * This paper examines alternative forms of match bias arising from earnings imputation. Wage equation parameters are estimated based on mixed samples of workers who do and do not report earnings, the latter group being assigned earnings of donors who share some but not all the attributes of the recipients. Regressions that include attributes not used as imputation match criteria (e.g., union status) are severely biased. Related forms of match bias arise with respect to attributes used as match criteria, but matched imperfectly. For example, an imperfect match on schooling creates bias that flattens estimated earnings profiles within low, middle, and high education groups, while creating large jumps in returns across groups. The same pattern arises in wage-age profiles. The paper provides a general analytic expression to correct match bias in regression coefficients under the assumption of conditional mean missing at random. The full sample correction approach is compared to the alternative of omitting imputed earners from the sample, with and without reweighting. Additional problems considered are bias in longitudinal analysis and the presence of dated donors.JEL Classification: J31, C81, C10

show abstract

Section: Introductionmentioning

confidence: 69%

Section: Introductionmentioning

confidence: 99%

Match Bias from Earnings Imputation in the Current Population Survey: The Case of Imperfect Matching

Bollinger

Hirsch

2006

Journal of Labor Economics

Self Cite

148

158

View full text Add to dashboard Cite

show abstract

“…We also do not exclude allocated earnings because (i) doing so might bias our estimate for the average wage and (ii) allocation flags are not available for all years and (iii) even if they are only about 25% of allocated observations are flagged as such (Hirsch and Schumacher 2004).…”

Section: B1 Wages From the Cps Outgoing Rotation Groupsmentioning

confidence: 99%

Wage rigidity and job creation

Hæfke

Sonntag²,

Rens

2013

Journal of Monetary Economics

152

View full text Add to dashboard Cite

Shimer (2005) and Hall (2005) have documented the failure of standard labor market search models to match business cycle fluctuations in employment and unemployment. They argue that it is likely that wages are not adjusted as regularly as suggested by the model, which would explain why employment is more volatile than the model predicts. We explore whether this explanation is consistent with the data. The main insight is that the relevant wage data for the search model are not aggregate wages, but wages of newly hired workers. Our results show that wages for those workers are much more volatile than aggregate wages and respond one-for-one to changes in labor productivity. Thus, we find no evidence for wage rigidity.JEL Codes: E24 E32 J31 J41 J64

show abstract

“…However, I checked that the inclusion or exclusion of the flagged imputed wages made virtually no difference to my results (cf. Hirsch and Schumacher, 2002).…”

Section: Datamentioning

confidence: 99%

“…Regression 205,424 209,560 210,288 207,097 205,829 203,028 200,607 Note: Changes between 1995 and 1996 in the CPS are explained by the changes in the imputation flags (cf. Hirsch and Schumacher, 2002). The large increase in the number of wage observations in the BLFS between 1996 and 1997 is explained by the fact that respondents were asked about their wage only in the 1 st quarter of interview up to 1996, but also in the 5 th quarter since 1997.…”

Section: Us (Cps) Britain (Blfs) Britain (Ghs) Germany (Iabr I) Germentioning

confidence: 99%

Transatlantic Differences in Labour Markets: Changes in Wage and Non-Employment Structures in the 1980s and the 1990s

Puhani

2005

SSRN Journal

View full text Add to dashboard Cite

Match Bias in Wage Gap Estimates Due to Earnings Imputation

Cited by 233 publications

References 28 publications

Match Bias from Earnings Imputation in the Current Population Survey: The Case of Imperfect Matching

Match Bias from Earnings Imputation in the Current Population Survey: The Case of Imperfect Matching

Wage rigidity and job creation

Transatlantic Differences in Labour Markets: Changes in Wage and Non-Employment Structures in the 1980s and the 1990s

Contact Info

Product

Resources

About