Estimation of Heterogeneous Treatment Effects Using a Conditional Moment Based Approach

28 Oct 2022  ·  Xiaolin Sun ·

We propose a new estimator for heterogeneous treatment effects in a partially linear model (PLM) with many exogenous covariates and a possibly endogenous treatment variable. The PLM has a parametric part that includes the treatment and the interactions between the treatment and exogenous characteristics, and a nonparametric part that contains those characteristics and many other covariates. The new estimator is a combination of a Robinson transformation to partial out the nonparametric part of the model, the Smooth Minimum Distance (SMD) approach to exploit all the information of the conditional mean independence restriction, and a Neyman-Orthogonalized first-order condition (FOC). With the SMD method, our estimator using only one valid binary instrument identifies both parameters. With the sparsity assumption, using regularized machine learning methods (i.e., the Lasso method) allows us to choose a relatively small number of polynomials of covariates. The Neyman-Orthogonalized FOC reduces the effect of the bias associated with the regularization method on estimates of the parameters of interest. Our new estimator allows for many covariates and is less biased, consistent, and $\sqrt{n}$-asymptotically normal under standard regularity conditions. Our simulations show that our estimator behaves well with different sets of instruments, but the GMM type estimators do not. We estimate the heterogeneous treatment effects of Medicaid on individual outcome variables from the Oregon Health Insurance Experiment. We find using our new method with only one valid instrument produces more significant and more reliable results for heterogeneous treatment effects of health insurance programs on economic outcomes than using GMM type estimators.

PDF Abstract
No code implementations yet. Submit your code now

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here