AI Paper Atlas

Research map / Probabilistic and scientific modeling / Treatment effects

Proximal Difference-in-Differences for Long-Term Causal Learning under Confounding and Outcome Drift

Sihyung Park, Shu Yang, Mingyang Shan, Wenyu Ye, Ilya Lipkovich

NeurIPS 2026 · Probabilistic and scientific modeling › Treatment effects · approach: Latent-variable causal inference

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a proximal difference-in-differences method to estimate long-term treatment effects by combining RCT data with real-world evidence under confounding and outcome drift.

Problem

Estimating long-term treatment effects when RCT follow-up is short and open-label extensions censor long-term control trajectories; existing RWE-supplementation methods are vulnerable to unobserved confounding and outcome drift.

Approach

Applies a proximal (proxy-variable) difference-in-differences identification strategy to handle unobserved confounding and temporal outcome drift when fusing RCT and real-world data for long-term causal effects.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use proximal doubly robust (PDR) estimator instead of baselineslong-term control trend · Alzheimer's plasmodebias: -0.005 vs -0.896 (MB), -0.607 (SDID), -0.537 (MC-NNM)Improved
use PDR rather than POR or PIPW under nuisance misspecification (ablation)proximal estimators · synthetic simulation (n=500, 500 reps)bias, coverage: POR and PIPW biased with poor coverage when a nuisance is misspecifiedImproved
use PDR with nonlinear data (gamma=2)PDR · synthetic simulationbias and coverage: modest bias, slight undercoverageMixed
use proximal PDR instead of SDID, MC-NNM, MBlong-term effect estimators · synthetic simulationbias and coverage: larger bias and lower coverage for baselinesImproved
strong proxy-Z violation (gamma_z 0.3 -> 1.5) (ablation)PDR · sensitivity simulationbias: -0.254 -> -0.866Hurt
strong proxy-W violation (gamma_w 0.05 -> 0.25) (ablation)PDR · sensitivity simulationbias: -0.142 -> -0.365Hurt
violate CPTL with trend acceleration alpha=0.5 (ablation)PDR vs benchmarks · sensitivity simulationbias: PDR -0.262 vs SDID -2.096Improved
moderate violation of W independence (ablation)PDR vs SDID · sensitivity simulationbias: PDR -0.365 vs SDID -0.120Hurt

Experimental setup

Builds on: difference-in-differences proximal causal inference

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy