9. Variance Function Regressions for Studying Inequality

Regression-based studies of inequality model only between-group differences, yet often these differences are far exceeded by residual inequality. Residual inequality is usually attributed to measurement error or the influence of unobserved characteristics. We present a model, called variance function regression, that includes covariates for both the mean and variance of a dependent variable. In this model, the residual variance is treated as a target for analysis. In analyses of inequality, the residual variance might be interpreted as measuring risk or insecurity. Variance function regressions are illustrated in an analysis of panel data on earnings among released prisoners in the National Longitudinal Survey of Youth. We extend the model to a decomposition analysis, relating the change in inequality to compositional changes in the population and changes in coefficients for the mean and variance. The decomposition is applied to the trend in U.S. earnings inequality among male workers, 1970 to 2005.

[1]  D. Pager.  The Mark of a Criminal Record1 , 2003, American Journal of Sociology.

[2]  Bruce Western,et al.  The Impact of Incarceration on Wage Mobility and Inequality , 2002, American Sociological Review.

[3]  Peter Selb.  Supersized votes: ballot length, uncertainty, and choice in direct legislation elections , 2008 .

[4]  J. Jannink,et al.  Bayesian Modeling of Heterogeneous Error and Genotype × Environment Interaction Variances , 2006 .

[5]  L. West,et al.  The Supply and Demand Factors , 2001 .

[6]  B. Western.  Punishment and inequality in America , 2006 .

[7]  A. B. Sørensen.  Toward a Sounder Basis for Class Analysis1 , 2000, American Journal of Sociology.

[8]  F. J. Anscombe,et al.  Examination of Residuals , 1961 .

[9]  D. Acemoglu.  Technical Change, Inequality, and the Labor Market , 2000 .

[10]  J. Dinardo,et al.  Labor Market Institutions and the Distribution of Wages, 1973-1992: A Semiparametric Approach , 1996 .

[11]  David Lam,et al.  Age, Experience, and Schooling: Decomposing Earnings Inequality in the United States and Brazil* , 1992 .

[12]  Gordon K. Smyth,et al.  An Efficient Algorithm for REML in Heteroscedastic Regression , 2002 .

[13]  Kevin M. Murphy,et al.  Wage Inequality and the Rise in Returns to Skill , 1993, Journal of Political Economy.

[14]  Charles Tilly,et al.  Durable Inequality , 2004 .

[15]  John A. Nelder,et al.  Generalized linear models for the analysis of Taguchi-type experiments , 1991 .

[16]  M. Aitkin.  Modelling variance heterogeneity in normal regression using GLIM , 1987 .

[17]  A. Moehlman,et al.  Inequality, A Reassessment of the Effect of Family and Schooling in America. , 1974 .

[18]  R. Murnane,et al.  U.S. Earnings Levels and Earnings Inequality: A Review of Recent Trends and Proposed Explanations , 1992 .

[19]  ChangHwan Kim,et al.  The Rise of Intra-Occupational Wage Inequality in the United States, 1983 to 2002 , 2008 .

[20]  P. Allison.  Measures of Inequality , 1978 .

[21]  Ransom A. Myers,et al.  Survival variability and population density in fish populations , 2008, Nature.

[22]  Robert Plomin,et al.  Sex differences in variance of intelligence across childhood. , 2006 .

[23]  L. McCall.  Explaining levels of within-group wage inequality in U.S. labor markets , 2000, Demography.

[24]  Gordon K. Smyth,et al.  Exact and approximate REML for heteroscedastic regression , 2001 .

[25]  G. Jasso,et al.  Two Types of Inequality , 2007 .

[26]  Olav Sorenson,et al.  Corporate Demography and Income Inequality , 2007 .

[27]  S. Weisberg,et al.  Diagnostics for heteroscedasticity in regression , 1983 .

[28]  A. Verbyla,et al.  Modelling Variance Heterogeneity: Residual Maximum Likelihood and Diagnostics , 1993 .

[29]  Thomas Lemieux,et al.  Increasing Residual Wage Inequality: Composition Effects, Noisy Data, or Rising Demand for Skill? , 2006 .

[30]  O. D. Duncan,et al.  The American Occupational Structure , 1967 .

[31]  Lawrence F. Katz,et al.  Trends in U.S. Wage Inequality: Re-Assessing the Revisionists , 2005 .

[32]  Paula England,et al.  The Wage Penalty for Motherhood , 2001, American Sociological Review.

[33]  Douglas S. Massey,et al.  Categorically Unequal: The American Stratification System , 2007 .

[34]  Jeffrey R. Kling,et al.  Incarceration Length, Employment, and Earnings , 2006 .

[35]  R. Park.  Estimation with Heteroscedastic Error Terms , 1966 .

[36]  E. O. Wright.  Class, Exploitation and Economic Rents: Reflections on Sørensen's " toward a Sounder Basis for Class Analysis " , 2000 .

[37]  A. Harvey.  Estimating Regression Models with Multiplicative Heteroscedasticity , 1976 .

[38]  Marshall S. Smith,et al.  Inequality: A Reassessment of the Effect of Family and Schooling in America , 1973 .

[39]  Matthew S. Lewis.  Price Dispersion and Competition with Differentiated Sellers , 2008 .

[40]  Yu Xie,et al.  Temporal and regional variation in earnings inequality: urban China in transition between 1988 and 1995 , 2005 .

[41]  David J. Maume,et al.  Reconsidering the declining significance of race : Racial differences in early career wages , 1996 .