Semiparametric Sensitivity Analysis: Unmeasured Confounding In Observational Studies

by   Daniel O. Scharfstein, et al.

Establishing cause-effect relationships from observational data often relies on untestable assumptions. It is crucial to know whether, and to what extent, the conclusions drawn from non-experimental studies are robust to potential unmeasured confounding. In this paper, we focus on the average causal effect (ACE) as our target of inference. We build on the work of Franks et al. (2019)and Robins (2000) by specifying non-identified sensitivity parameters that govern a contrast between the conditional (on measured covariates) distributions of the outcome under treatment (control) between treated and untreated individuals. We use semiparametric theory to derive the non-parametric efficient influence function of the ACE, for fixed sensitivity parameters. We use this influence function to construct a one-step bias-corrected estimator of the ACE. Our estimator depends on semiparametric models for the distribution of the observed data; importantly, these models do not impose any restrictions on the values of sensitivity analysis parameters. We establish sufficient conditions ensuring that our estimator has root-n asymptotics. We use our methodology to evaluate the causal effect of smoking during pregnancy on birth weight. We also evaluate the performance of estimation procedure in a simulation study.


page 1

page 2

page 3

page 4


Sensitivity Analysis of Causal Treatment Effect Estimation for Clustered Observational Data with Unmeasured Confounding

Identifying causal treatment (or exposure) effects in observational stud...

A coherent likelihood parametrization for doubly robust estimation of a causal effect with missing confounders

Missing data and confounding are two problems researchers face in observ...

Bounds and semiparametric inference in L^∞- and L^2-sensitivity analysis for observational studies

Sensitivity analysis for the unconfoundedness assumption is a crucial co...

A Semiparametric Approach to Model-based Sensitivity Analysis in Observational Studies

When drawing causal inference from observational data, there is always c...

Sense and Sensitivity Analysis: Simple Post-Hoc Analysis of Bias Due to Unobserved Confounding

It is a truth universally acknowledged that an observed association with...

Sensitivity Analysis under the f-Sensitivity Models: Definition, Estimation and Inference

The digitization of the economy has witnessed an explosive growth of ava...

Please sign up or login with your details

Forgot password? Click here to reset