Estimating wage differentials without logarithms

Abstract Regression models of wage determination are typically estimated by ordinary least squares using the logarithm of the wage as the dependent variable. These models provide consistent estimates of the proportional impact of wage determinants only under the assumption that the distribution of the error term is independent of the regressors — an assumption that can be violated by the presence of heteroskedasticity, for example. Failure of this assumption is particularly relevant in the estimation of the impact of union status on wages. Alternative wage-equation estimators based on the use of quasi-maximum-likelihood methods are consistent under weaker assumptions about the dependence between the error term and the regressors. They also provide the ability to check the specification of the underlying wage model. Applying this approach to a standard data set, I find that the impact of unions on wages is overstated by a magnitude of 20-30 percent when estimates from log-wage regressions are used for inference.

[1]  Chandra Shah,et al.  Exact Interpretation of Dummy Variables in Semilogarithmic Equations , 2002 .

[2]  N. Duan.  Smearing Estimate: A Nonparametric Retransformation Method , 1983 .

[3]  T. Lemieux.  The “Mincer Equation” Thirty Years After Schooling, Experience, and Earnings , 2006 .

[4]  R. Tibshirani,et al.  An introduction to the bootstrap , 1993 .

[5]  H. White.  Maximum Likelihood Estimation of Misspecified Models , 1982 .

[6]  Peter E. Kennedy.  Estimation with Correctly Interpreted Dummy Variables in Semilogarithmic Equations , 1981 .

[7]  Richard B. Freeman,et al.  Longitudinal Analyses of the Effects of Trade Unions , 1983, Journal of Labor Economics.

[8]  David Card.  THE EFFECT OF UNIONS ON THE STRUCTURE OF WAGES: A LONGITUDINAL ANALYSIS , 1996 .

[9]  Jeffrey M. Wooldridge,et al.  Some Alternatives to the Box-Cox Regression Model , 1992 .

[10]  Christian Gourieroux,et al.  Statistics and econometric models , 1995 .

[11]  J. Mincer.  Schooling, Experience, and Earnings , 1976 .

[12]  R. Halvorsen,et al.  The Interpretation of Dummy Variables in Semilogarithmic Equations , 1980 .

[13]  J. Wooldridge.  Distribution-free estimation of some nonlinear panel data models , 1999 .

[14]  P. Schmidt,et al.  Limited-Dependent and Qualitative Variables in Econometrics. , 1984 .

[15]  Jeffrey M. Wooldridge,et al.  Quasi‐Likelihood Methods for Count Data , 2008 .

[16]  B. Hirsch,et al.  Unions, Wages, and Skills , 1998 .

[17]  Peter E. Kennedy.  A Guide to Econometrics , 1979 .

[18]  Pravin K. Trivedi,et al.  Regression Analysis of Count Data , 1998 .

[19]  Jeffrey M. Wooldridge,et al.  Solutions Manual and Supplementary Materials for Econometric Analysis of Cross Section and Panel Data , 2003 .

[20]  C. Ai,et al.  Standard errors for the retransformation problem with heteroscedasticity. , 2000, Journal of health economics.

[21]  H. Lewis.  Chapter 20 Union relative wage effects , 1986 .

[22]  C. Gouriéroux,et al.  PSEUDO MAXIMUM LIKELIHOOD METHODS: THEORY , 1984 .

[23]  Jeffrey M. Wooldridge,et al.  Specification testing and quasi-maximum-likelihood estimation , 1991 .

[24]  W. Manning,et al.  The logged dependent variable, heteroscedasticity, and the retransformation problem. , 1998, Journal of health economics.

[25]  James L. Medoff,et al.  What Do Unions Do , 1986 .

[26]  G. Judge,et al.  The Theory and Practice of Econometrics , 1981 .

[27]  Z. Griliches,et al.  Econometric Models for Count Data with an Application to the Patents-R&D Relationship , 1984 .

[28]  Petra E. Todd,et al.  Fifty Years of Mincer Earnings Regressions , 2003, SSRN Electronic Journal.

[29]  David Card,et al.  The Effect of Unions on Wage Inequality in the U.S. Labor Market , 2001 .

[30]  J. Wolfowitz,et al.  Introduction to the Theory of Statistics. , 1951 .