Kernel Methods for Causal Functions: Dose, Heterogeneous, and Incremental Response Curves
This provides a method for estimating causal functions in complex settings, which is important for researchers and practitioners in econometrics and policy evaluation, though it appears incremental as an extension of kernel methods to causal inference.
The authors developed kernel ridge regression estimators for nonparametric causal functions like dose, heterogeneous, and incremental response curves, handling discrete or continuous treatments and covariates in general spaces. They proved uniform consistency with finite sample rates and demonstrated state-of-the-art performance in nonlinear simulations with many covariates, plus a policy evaluation of the US Job Corps training program.
We propose estimators based on kernel ridge regression for nonparametric causal functions such as dose, heterogeneous, and incremental response curves. Treatment and covariates may be discrete or continuous in general spaces. Due to a decomposition property specific to the RKHS, our estimators have simple closed form solutions. We prove uniform consistency with finite sample rates via original analysis of generalized kernel ridge regression. We extend our main results to counterfactual distributions and to causal functions identified by front and back door criteria. We achieve state-of-the-art performance in nonlinear simulations with many covariates, and conduct a policy evaluation of the US Job Corps training program for disadvantaged youths.