This paper studies non-separable models with a continuous treatment when the dimension of the control variables is high and potentially larger than the effective sample size. We propose a three-step estimation procedure to estimate the average, quantile, and marginal treatment effects. In the first stage we estimate the conditional mean, distribution, and density objects by penalized local least squares, penalized local maximum likelihood estimation, and numerical differentiation, respectively, where control variables are selected via a localized method of L 1 -penalization at each value of the continuous treatment. In the second stage we estimate the average and marginal distribution of the potential outcome via the plug-in principle. In the third stage, we estimate the quantile and marginal treatment effects by inverting the estimated distribution function and using the local linear regression, respectively. We study the asymptotic properties of these estimators and propose a weighted-bootstrap method for inference. Using simulated and real datasets, we demonstrate that the proposed estimators perform well in finite samples.Econometricians observe an outcome Y , a continuous treatment T , and a set of covariates X, which may be high-dimensional. They are connected by a measurable function Γ(·), i.e.,where A is an unobservable random vector and may not be weakly separable from observables (T, X), and Γ may not be monotone in either T or A.Let Y (t) = Γ(t, X, A). We are interested in the average EY (t), the marginal distribution P(Y (t) ≤ u) for some u ∈ , and the quantile q τ (t), where we denote q τ (t) as the τ -th quantile of Y (t) for some τ ∈ (0, 1). We are also interested in the causal effect of moving T from t to t , i.e., E(Y (t) − Y (t )) and q τ (t) − q τ (t ). Last, we are interested in the average marginal effect E[∂ t Γ(t, X, A)] and quantile partial derivative ∂ t q τ (t). Next, we specify conditions under which the above parameters are identified.
Assumption 1The random variables A and T are conditionally independent given X.Assumption 1 is known as the unconfoundedness condition, which is commonly assumed in the treatment effect literature. See Cattaneo (2010), Cattaneo and Farrell (2011), Hirano et al. (2003) and Firpo (2007) for the case of discrete treatment and Graham, Imbens, and Ridder (2014), Galvao and Wang (2015), and Hirano and Imbens (2004) for the case of continuous treatment. It is also called the conditional independence assumption in Hoderlein and Mammen (2007), which is weaker than the full joint independence between A and (T, X). Note that X can be arbitrarily correlated with the unobservables A. This assumption is more plausible when we control for sufficiently many and potentially high-dimensional covariates.Theorem 2.1 Suppose Assumption 1 holds and Γ(·) is differentiable in its first argument. Then the marginal distribution of Y (t) and the average marginal effect ∂ t EY (t) are identified. In addition, if Assumption 6 in the Appendix holds and X is continuously distribute...