A Neural Framework for Generalized Causal Sensitivity Analysis

TL;DR

NeuralCSA is a neural network-based framework that provides flexible and theoretically guaranteed bounds for causal effects under unobserved confounding across various models, treatment types, and causal queries.

Contribution

It introduces NeuralCSA, a versatile neural framework capable of handling multiple sensitivity models, treatment types, and causal queries with theoretical guarantees.

Findings

NeuralCSA accurately infers bounds on causal effects in simulated data.

It demonstrates practical applicability on real-world observational data.

The framework generalizes previous methods to broader sensitivity models and treatment types.

Abstract

Unobserved confounding is common in many applications, making causal inference from observational data challenging. As a remedy, causal sensitivity analysis is an important tool to draw causal conclusions under unobserved confounding with mathematical guarantees. In this paper, we propose NeuralCSA, a neural framework for generalized causal sensitivity analysis. Unlike previous work, our framework is compatible with (i) a large class of sensitivity models, including the marginal sensitivity model, f-sensitivity models, and Rosenbaum's sensitivity model; (ii) different treatment types (i.e., binary and continuous); and (iii) different causal queries, including (conditional) average treatment effects and simultaneous effects on multiple outcomes. The generality of NeuralCSA is achieved by learning a latent distribution shift that corresponds to a treatment intervention using two conditional normalizing flows. We provide theoretical guarantees that NeuralCSA is able to infer valid bounds on the causal query of interest and also demonstrate this empirically using both simulated and real-world data.