On Measurement Bias in Causal Inference

TL;DR

This paper explores how measurement errors affect causal inference and presents algebraic and graphical methods to eliminate systematic bias caused by such errors, focusing on confounder control and bias-free effect estimation.

Contribution

It introduces novel algebraic and graphical techniques for controlling measurement bias in causal inference models, addressing both parametric and non-parametric cases.

Findings

Methods for eliminating measurement bias in causal models.

Techniques for controlling partially observable confounders.

Approaches for bias-free effect estimation in complex models.

Abstract

This paper addresses the problem of measurement errors in causal inference and highlights several algebraic and graphical methods for eliminating systematic bias induced by such errors. In particulars, the paper discusses the control of partially observable confounders in parametric and non parametric models and the computational problem of obtaining bias-free effect estimates in such models.