TY - JOUR AU - Barsky,Robert AU - Bound,John AU - Charles,Kerwin AU - Lupton,Joseph TI - Accounting for the Black-White Wealth Gap: A Nonparametric Approach JF - National Bureau of Economic Research Working Paper Series VL - No. 8466 PY - 2001 Y2 - September 2001 UR - http://www.nber.org/papers/w8466 L1 - http://www.nber.org/papers/w8466.pdf N1 - Author contact info: Robert B. Barsky Department of Economics University of Michigan Ann Arbor, MI 48109-1220 Tel: 734/764-9476 Fax: 734/764-2769 E-Mail: barsky@umich.edu John Bound Department of Economics University of Michigan Ann Arbor, MI 48109-1220 Tel: 734/998-7149 Fax: 734/998-7415 E-Mail: jbound@umich.edu Kerwin Kofi Charles Harris School of Public Policy University of Chicago 1155 East 60th Street Chicago, IL 60637 Tel: 773.834.8922 Fax: NA E-Mail: kcharles@uchicago.edu Joseph Lupton E-Mail: joseph.p.lupton@frb.gov AB - This paper notes a potential problem in the method of Blinder and Oaxaca the most popular method in the literature for decomposing the mean difference between groups of a given variable into the portion attributable to differences in the distribution of some explanatory variables and differences in the conditional expectation functions. In its conventional application, the Blinder-Oaxaca method requires that a parametric assumption be made about the form of the conditional expectations function. We show that misspecification is likely to result in non-trivial errors in inference regarding the portion attributable to differences in the distribution of explanatory variables. A nonparametric alternative to the Blinder-Oaxaca method is proposed. Rather than specify an arbitrary functional form for the conditional expectations function, the method re-weights the empirical distribution of the outcome variable using weights that equalize the empirical distributions of the explanatory variable. Applying this method to the large black-white gap in net worth, we document a substantial difference in the estimated role of earnings differences between the two methods. Our estimates suggest that differences in earnings account for roughly two-thirds of the overall wealth gap. ER -