Obtaining a Consistent Estimate of the Elasticity of Taxable Income Using Difference-in-Differences

The elasticity of taxable income (ETI) is a central parameter for tax policy debates. This paper shows that most estimators employed in the literature fail to obtain consistent estimates of the ETI. A new method is proposed that will provide consistent estimates under testable assumptions regarding the degree of serial correlation in the error term. Using this procedure, I estimate an ETI of 1.046, which is more than twice as large as the estimates found in the most frequently cited paper on this subject (Gruber and Saez, 2002). I also consider an alternative definition of treatment, which was proposed in Weber (2011). It has a minimal effect on the estimates, but decreases standard errors by 16 percent. Many thanks to David Agrawal, Gerald Auten, Dora Benedek, Alexander Gelber, Jim Hines, Laura Kawano, Emmanuel Saez, Hȧkan Selin, Joel Slemrod, Jeff Smith, two anonymous referees, University of Michigan seminar participants, and International Institute of Public Finance 2010 conference participants for helpful comments. Also, thanks to Dan Feenberg for his help with the TAXSIM calculator. And, a special thanks to Emmanuel Saez for giving me the code used in Gruber and Saez (2002). All remaining errors are my own. *Ph.D. Candidate, Department of Economics, University of Michigan: [email protected]. JEL Codes: H21, H24