Nonparametric Bounds and Sensitivity Analysis of Treatment Effects

TL;DR

This paper explores methods for inference about treatment effects when the effect is only partially identifiable, using bounds and sensitivity analysis in observational and noncompliance settings.

Contribution

It provides a comprehensive review of bounds and sensitivity analysis approaches for treatment effects under partial identifiability, including formal inference methods.

Findings

Bounds can be derived under minimal assumptions.

Sensitivity analysis assesses impact of untestable assumptions.

Methods apply to principal strata and time-varying exposures.

Abstract

This paper considers conducting inference about the effect of a treatment (or exposure) on an outcome of interest. In the ideal setting where treatment is assigned randomly, under certain assumptions the treatment effect is identifiable from the observable data and inference is straightforward. However, in other settings such as observational studies or randomized trials with noncompliance, the treatment effect is no longer identifiable without relying on untestable assumptions. Nonetheless, the observable data often do provide some information about the effect of treatment, that is, the parameter of interest is partially identifiable. Two approaches are often employed in this setting: (i) bounds are derived for the treatment effect under minimal assumptions, or (ii) additional untestable assumptions are invoked that render the treatment effect identifiable and then sensitivity analysis is conducted to assess how inference about the treatment effect changes as the untestable assumptions are varied. Approaches (i) and (ii) are considered in various settings, including assessing principal strata effects, direct and indirect effects and effects of time-varying exposures. Methods for drawing formal inference about partially identified parameters are also discussed.