• Corpus ID: 237289724

Nonparametric identification is not enough, but randomized controlled trials are

  title={Nonparametric identification is not enough, but randomized controlled trials are},
  author={Peter M. Aronow and James M. Robins and Theo Saarinen and Fredrik Savje and Jasjeet S. Sekhon},
We argue that randomized controlled trials (RCTs) are special even among settings where average treatment effects are identified by a nonparametric unconfoundedness assumption. This claim follows from two results of Robins and Ritov (1997): (1) with at least one continuous covariate control, no estimator of the average treatment effect exists which is uniformly consistent without further assumptions, (2) knowledge of the propensity score yields a consistent estimator and confidence intervals at… 

Figures from this paper

Causal Effect Variational Autoencoder with Uniform Treatment

Uniform treatment variational autoencoders (UTVAE) that are trained with uniform treatment distribution using importance sampling are introduced and it is shown that using uniform treatment over observational treatment distribution leads to better causal inference by mitigating the distribution shift that occurs from training to test time.

Positivity: Identifiability and Estimability

Positivity, the assumption that every unique combination of confounding variables that occurs in a population has a non-zero probability of an action, can be further delineated as deterministic

Online Balanced Experimental Design

This work presents algorithms that build on recent advances in online discrepancy minimization which accommodate both arbitrary treatment probabilities and multiple treatments, and includes randomization which enables robustness to misspecification.



The LOOP Estimator: Adjusting for Covariates in Randomized Experiments

This article proposes the “leave-one-out potential outcomes” estimator, a covariate adjustment method that allows for automatic variable selection, so that practitioners need not commit to any specific set of covariates prior to seeing the data.

Lasso adjustments of treatment effect estimates in randomized experiments

Simulation and data examples show that Lasso-based adjustment can be advantageous even when the number of covariates is less than theNumber of observations, and a variant using Lasso for selection and ordinary least squares for estimation performs particularly well, and it chooses a smoothing parameter based on combined performance of Lasso and OLS.

Efficient Estimation of Average Treatment Effects Using the Estimated Propensity Score

It is shown that weighting with the inverse of a nonparametric estimate of the propensity Score, rather than the true propensity score, leads to efficient estimates of the various average treatment effects, whether the pre-treatment variables have discrete or continuous distributions.

Causaltoolbox—Estimator Stability for Heterogeneous Treatment Effects

Estimating heterogeneous treatment effects has become extremely important in many fields and often life changing decisions for individuals are based on these estimates, for example choosing a medical

A Unified Theory of Regression Adjustment for Design-based Inference

Under the Neyman causal model, it is well-known that OLS with treatment-by-covariate interactions cannot harm asymptotic precision of estimated treatment effects in completely randomized experiments.

Finite-Sample Optimal Estimation and Inference on Average Treatment Effects Under Unconfoundedness

We consider estimation and inference on average treatment effects under unconfoundedness conditional on the realizations of the treatment variable and covariates. Given nonparametric smoothness

Optimal doubly robust estimation of heterogeneous causal effects

A two-stage doubly robust CATE estimator is studied and a generic model-free error bound is given and it is shown that this estimator can be oracle efficient under even weaker conditions, if used with a specialized form of sample splitting and careful choices of tuning parameters.

Robust Inference on Average Treatment Effects with Possibly More Covariates than Observations

Double/Debiased Machine Learning for Treatment and Causal Parameters

This work can form an orthogonal score for the target low-dimensional parameter by combining auxiliary and main ML predictions, and build a de-biased estimator of the target parameter which typically will converge at the fastest possible 1/root(n) rate and be approximately unbiased and normal, and from which valid confidence intervals for these parameters of interest may be constructed.

Randomization does not imply unconfoundedness

A common assumption in causal inference is that random treatment assignment ensures that potential outcomes are independent of treatment, or in one word, unconfoundedness. This paper highlights that