Estimating Treatment Effects using Multiple Surrogates: The Role of the Surrogate Score and the Surrogate Index

TL;DR

This paper develops methods to estimate long-term treatment effects using multiple surrogate outcomes, leveraging high-dimensional data and two-sample designs to address challenges in causal inference when direct long-term outcomes are unobserved.

Contribution

It introduces a framework for using multiple proxies in causal inference, establishing conditions for identification and analyzing bias under surrogacy violations.

Findings

High-dimensional surrogate vectors can identify treatment effects.

Bias analysis under surrogacy violations informs estimator robustness.

Using surrogates in two-sample settings improves long-term effect estimation.

Abstract

Estimating the long-term effects of treatments is of interest in many fields. A common challenge in estimating such treatment effects is that long-term outcomes are unobserved in the time frame needed to make policy decisions. One approach to overcome this missing data problem is to analyze treatments effects on an intermediate outcome, often called a statistical surrogate, if it satisfies the condition that treatment and outcome are independent conditional on the statistical surrogate. The validity of the surrogacy condition is often controversial. Here we exploit that fact that in modern datasets, researchers often observe a large number, possibly hundreds or thousands, of intermediate outcomes, thought to lie on or close to the causal chain between the treatment and the long-term outcome of interest. Even if none of the individual proxies satisfies the statistical surrogacy criterion by itself, using multiple proxies can be useful in causal inference. We focus primarily on a setting with two samples, an experimental sample containing data about the treatment indicator and the surrogates and an observational sample containing information about the surrogates and the primary outcome. We state assumptions under which the average treatment effect be identified and estimated with a high-dimensional vector of proxies that collectively satisfy the surrogacy assumption, and derive the bias from violations of the surrogacy assumption, and show that even if the primary outcome is also observed in the experimental sample, there is still information to be gained from using surrogates.