Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
We explore elasticity heterogeneity in the estimation of the elasticity of taxable income (ETI) and propose potentially valid instruments. We show that previously used instruments are not valid and yield weighted averages of ETIs of different taxpayers plus a bias. Using the NBER tax panel for 1979–1990, we find a weighted average ETI of 0.57 when using all available variation in budget set changes provided by the tax reforms in the data. Our results also demonstrate that elasticity heterogeneity is an important explanation for the remarkable divergence of estimates in the previous literature.