Markov-Restricted Analysis of Randomized Trials with Non-Monotone Missing Binary Outcomes

TL;DR

This paper introduces a Markovian restriction approach to improve the computational feasibility of sensitivity analysis models for large-scale randomized trials with nonmonotone missing binary outcomes, enabling better joint distribution estimation.

Contribution

It proposes mth-order Markovian restrictions and a novel estimation strategy, addressing computational challenges in analyzing complex missing data patterns in randomized trials.

Findings

Established identification of joint distribution using DAGs.

Developed a new estimation method for smooth functionals.

Applied methodology to a substance use trial with weekly abstinence data.

Abstract

Scharfstein et al. (2021) developed a sensitivity analysis model for analyzing randomized trials with repeatedly measured binary outcomes that are subject to nonmonotone missingness. Their approach becomes computationally intractable when the number of measurements is large (e.g., greater than 15). In this paper, we repair this problem by introducing mth-order Markovian restrictions. We establish identification results for the joint distribution of the binary outcomes by representing the model as a directed acyclic graph (DAG). We develop a novel estimation strategy for a smooth functional of the joint distribution. We illustrate our methodology in the context of a randomized trial designed to evaluate a web-delivered psychosocial intervention to reduce substance use, assessed by evaluating abstinence twice weekly for 12 weeks, among patients entering outpatient addiction treatment.