Non‐parametric methods for doubly robust estimation of continuous treatment effects

  title={Non‐parametric methods for doubly robust estimation of continuous treatment effects},
  author={Edward H. Kennedy and Zongming Ma and Matthew D. McHugh and Dylan S. Small},
  journal={Journal of the Royal Statistical Society: Series B (Statistical Methodology)},
Continuous treatments (e.g. doses) arise often in practice, but many available causal effect estimators are limited by either requiring parametric models for the effect curve, or by not allowing doubly robust covariate adjustment. We develop a novel kernel smoothing approach that requires only mild smoothness assumptions on the effect curve and still allows for misspecification of either the treatment density or outcome regression. We derive asymptotic properties and give a procedure for data… 

Improved inference for doubly robust estimators of heterogeneous treatment effects

We propose a doubly robust approach to characterizing treatment effect heterogeneity in observational studies. We develop a frequentist inferential procedure that utilizes posterior distributions for

Kernel Methods for Causal Functions: Dose, Heterogeneous, and Incremental Response Curves

This work proposes estimators based on kernel ridge regression for nonparametric causal functions such as dose, heterogeneous, and incremental response curves and proves uniform consistency with sample rates via original analysis of generalizedkernel ridge regression.

Covariate balancing for causal inference on categorical and continuous treatments

Causal Bias Quantification for Continuous Treatment

In this work we develop a novel characterization of marginal causal effect and causal bias in the continuous treatment setting. We show they can be expressed as an expectation with respect to a

Quantile Continuous Treatment Effects

Abstract Continuous treatments (e.g., doses) arise often in practice. Methods for estimation and inference for quantile treatment effects models with a continuous treatment are proposed.

Kernel Methods for Multistage Causal Inference: Mediation Analysis and Dynamic Treatment Effects

This work proposes kernel ridge regression estimators for mediation analysis and dynamic treatment effects over short horizons of the US Job Corps program for disadvantaged youth and proves uniform consistency with finite sample rates and semiparametric efficiency.

A nonparametric doubly robust test for a continuous treatment effect

The vast majority of literature on evaluating the significance of a treatment effect based on observational data has been confined to discrete treatments. These methods are not applicable to drawing

Efficient estimation of modified treatment policy effects based on the generalized propensity score

Continuous treatments have posed a significant challenge for causal inference, both in the formulation and identification of scientifically meaningful effects and in their robust estimation.

Non-parametric causal effects based on longitudinal modified treatment policies

Most causal inference methods consider counterfactual variables under interventions that set the treatment deterministically. With continuous or multi-valued treatments or exposures, such



Uniformly Semiparametric Efficient Estimation of Treatment Effects With a Continuous Treatment

This article studies identification, estimation, and inference of general unconditional treatment effects models with continuous treatment under the ignorability assumption. We show identification of

Causal Inference With General Treatment Regimes

In this article we develop the theoretical properties of the propensity function, which is a generalization of the propensity score of Rosenbaum and Rubin. Methods based on the propensity score have

The Role of the Propensity Score in Estimating Dose-Response Functions

Estimation of average treatment effects in observational, or non-experimental in pre-treatment variables. If the number of pre-treatment variables is large, and their distribution varies

Extending Marginal Structural Models through Local, Penalized, and Additive Learning

How marginal structural models for causal effects can be extended through the alternative techniques of local, penalized, and additive learning is shown, and nonparametric function estimation methods can be fruitfully applied for making causal inferences.

Targeted Data Adaptive Estimation of the Causal Dose–Response Curve

Abstract Estimation of the causal dose–response curve is an old problem in statistics. In a non-parametric model, if the treatment is continuous, the dose–response curve is not a pathwise

Demystifying Double Robustness: A Comparison of Alternative Strategies for Estimating a Population Mean from Incomplete Data

When outcomes are missing for reasons beyond an investigator's control, there are two different ways to adjust a parameter estimate for covariates that may be related both to the outcome and to

Bayesian Nonparametric Modeling for Causal Inference

Researchers have long struggled to identify causal effects in nonexperimental settings. Many recently proposed strategies assume ignorability of the treatment assignment mechanism and require fitting

Population Intervention Causal Effects Based on Stochastic Interventions

A new causal parameter is defined that takes into account the fact that intervention policies can result in stochastically assigned exposures, and inverse probability of treatment weighting, augmented IPTW, and targeted maximum likelihood estimators (TMLE) are developed.

Marginal Structural Models versus Structural nested Models as Tools for Causal inference

This paper describes an alternative new class of causal models — the (non-nested) marginal structural models (MSMs) and describes a class of semiparametric estimators for the parameters of these new models under a sequential randomization assumption.

A Doubly Robust Censoring Unbiased Transformation

It is shown that a mapping introduced in another statistical context is in fact a censoring unbiased transformation with a beneficial double robustness property, in that it can be used for nonparametric regression if either of these two conditional distributions are estimated accurately.