Research map / Probabilistic and scientific modeling / Causal discovery
Causal Discovery Using Regression-Based Conditional Independence Tests
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 RCIT (regression residual independence) instead of partial correlation for CI test | conditional independence testing · medical data D indep U given C | p-value: 0.0037 -> 0.1827 | Helped |
| use PC with RCIT instead of PC with KCIT, small samples (<200) | causal skeleton discovery · random 4-variable nonlinear ANM DAGs | F1 (skeleton) | Helped |
| use PC with RCIT instead of PC with KCIT, sample size 400 | causal skeleton discovery · random 4-variable nonlinear ANM DAGs | F1 (skeleton): about 0.016 better | No clear effect |
| use PC with RCIT instead of PC with KCIT | PDAG discovery · random 4-variable DAGs | PDAG recall/precision/F1 | Helped |
| use RCIT instead of KCIT, conditioning set size 1 or 2 | CI testing · synthetic Cases I and II | Type I/II error | No clear effect |
| use RCIT instead of KCIT, CIPERM and partial correlation with larger Z | CI testing · synthetic Cases I and II, n=100/200 | Type II error | Helped |
| use RCIT instead of KCIT, CIPERM and partial correlation | CI testing · synthetic Case I, D=3 | Type I error | Helped |
| use PC-RCIT instead of PC-KCIT in direction inference on 7-variable ANM | causal direction inference · Mooij et al. 2009 data, 1000 samples | edge direction correctness | Helped |
| increase sample size from 100 to 200 | RCIT, KCIT, CIPERM, partial correlation · synthetic Type I error | Type I error | No clear effect |
Closest papers by meaning
- Causal Discovery via Conditional Independence Testing with Proxy Variables (ICML 2024 · similarity 0.92)
- A Conditional Independence Test in the Presence of Discretization (ICLR 2025 · similarity 0.91)
- On the sample complexity of conditional independence testing with Von Mises estimator with application to causal discovery (ICML 2024 · similarity 0.91)
- PAIR-CI: Calibrated Conditional Independence Testing for Causal Discovery with Incomplete Data (NeurIPS 2026 · similarity 0.90)
- Testing Causal Models with Hidden Variables in Polynomial Delay via Conditional Independencies (AAAI 2025 · similarity 0.89)
- Causal Discovery with Fewer Conditional Independence Tests (ICML 2024 · similarity 0.89)
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.