Research map / Probabilistic and scientific modeling / Treatment effects
Estimation and inference on high-dimensional individualized treatment rule in observational data using split-and-pooled de-correlated score
Muxuan Liang, Young-Geun Choi, Yang Ning, Maureen A Smith, Ying-Qi Zhao
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use penalized doubly robust PEARL instead of Q-learning | Individualized treatment rule · Type-II diabetes EHR | value function: 0.869 -> 0.877 | Improved |
| apply PEARL rule instead of observed clinical practice | Individualized treatment rule · Type-II diabetes EHR | value function: 0.860 -> 0.877 | Improved |
| apply Q-learning rule instead of observed clinical practice | Individualized treatment rule · Type-II diabetes EHR | value function: 0.860 -> 0.869 | Improved |
| use PEARL with split-and-pooled score instead of Q-learning when the outcome model is nonlinear | Scenario II simulation · Simulation scenario II (xi=0.8, p=2500) | value function | Improved |
| use PEARL instead of Q-learning when the outcome model is linear and correctly specified | Scenario I simulation · Simulation scenario I (xi=0.7, p=2500) | value function | Hurt |
| use PEARL inference instead of Q-learning inference for power | Scenario II simulation · Simulation scenario II | power of tests | Improved |
| use PEARL inference instead of Q-learning inference for power | Scenario I simulation · Simulation scenario I | power and type I error | No clear effect |
| use PEARL value inference instead of Q-learning value inference | Value confidence interval · Simulation scenarios I and II | coverage of value | Improved |
Closest papers by meaning
- Efficient augmentation and relaxation learning for individualized treatment rules using observational data (JMLR 2019 · similarity 0.88)
- An effective framework for estimating individualized treatment rules (NeurIPS 2024 · similarity 0.87)
- Doubly Robust Fusion of Many Treatments for Policy Learning (ICML 2025 · similarity 0.84)
- Conformal Inference of Individual Treatment Effects Using Conditional Density Estimates (AAAI 2025 · similarity 0.83)
- PairNet: Training with Observed Pairs to Estimate Individual Treatment Effect (ICML 2024 · similarity 0.83)
- Doubly robust identification of treatment effects from multiple environments (ICLR 2025 · similarity 0.82)
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.
