Large-Scale Education Reform in General Equilibrium: Regression Discontinuity Evidence from India

Comment

Abstract

This paper reanalyzes Khanna (2023a), which studies labor market effects of schooling in India through regression discontinuity designs. Absent from the data are four districts close to the discontinuity. The absence is nonrandom and unexplained. Reversing it cuts the reduced-form impacts on schooling and log wages by 57% and 63%. Using regression-specific optimal bandwidths and a robust variance estimator clustered at the geographic unit of treatment makes impacts statistically indistinguishable from 0. This finding is robust to varying the identifying threshold and the bandwidth. The estimates of general equilibrium effects and elasticities of substitution are not unbiased and have effectively infinite first and second moments.