AI Paper Atlas

Research map / Probabilistic and scientific modeling / Treatment effects

Incorporating external data for analyzing randomized clinical trials: A transfer learning approach

Yujia Gu, Hanzhong Liu, Wei Ma

JMLR 2026 · Probabilistic and scientific modeling › Treatment effects · approach: Meta-learners and partial identification · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add bias-corrected transfer from source trial instead of lasso on target alonelasso-adjusted estimator · Synthetic Nefazodone CBASP trial, tau_1variance reduction vs benchmark (%): 25.53 -> 29.36Improved
add bias-corrected transfer from source trial instead of lasso on target alonelasso-adjusted estimator · Synthetic Nefazodone CBASP trial, tau_2variance reduction vs benchmark (%): 32.25 -> 40.19Improved
add bias-corrected transfer instead of lasso onlylasso-adjusted estimator · Synthetic Nefazodone CBASP trial, tau_295% CI coverage probability: 0.913 -> 0.950Improved
use source-only coefficients without bias correctionunadjusted benchmark · Synthetic Nefazodone CBASP trial, tau_1variance reduction vs benchmark (%): -35.08Hurt
increase covariate dimension s beyond s log p < sqrt(n) (ablation)lasso-adjusted estimator · Simulation Case 195% CI coverageHurt
add transfer learning when s is largelasso-adjusted estimator · Simulation Case 1sampling standard deviationImproved
add transfer learning when s is smalllasso-adjusted estimator · Simulation Case 1sampling standard deviationNo clear effect
misspecify source or target model (Cases 2 and 3) (ablation)transfer learning estimator · Simulation Cases 2 and 395% CI coverageNo clear effect
increase source-target bias h to 1 (ablation)transfer learning estimator · Simulation Case 195% CI coverageHurt

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