AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Decorrelated Variable Importance

Isabella Verdinelli, Larry Wasserman

JMLR 2024 · Probabilistic and scientific modeling › Causal discovery · approach: Counterfactual identification and bounds

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
use decorrelated parameter psi_3 instead of LOCO psi_Ladditive-model estimator · Synthetic Example 2confidence interval coverage: 0.00 -> 0.97Improved
use psi_3 instead of psi_Ladditive-model estimator · Synthetic Example 3confidence interval coverage: 0.00 -> 0.92Improved
use psi_3 instead of psi_Lrandom forest estimator · Synthetic Example 5confidence interval coverage: 0.00 -> 1.00Improved
use psi_3 instead of psi_Llinear-model estimator · Synthetic Example 5confidence interval coverage: 0.00 -> 0.00No clear effect
use psi_3 instead of psi_Lrandom forest estimator · Synthetic Example 2confidence interval coverage: 0.00 -> 0.30Hurt
use psi_3 instead of psi_Llinear-model estimator · Synthetic Example 3confidence interval coverage: 0 -> 0.99Improved
use psi_0 (nonparametric decorrelated) instead of psi_3additive-model estimator · Synthetic Example 4confidence interval coverage: 0.20 -> 0.98Hurt
use psi_0 instead of psi_3random forest estimator · Synthetic Example 3confidence interval coverage: 0 -> 0.91Hurt
use psi_2 instead of psi_3random forest estimator · Synthetic Example 2confidence interval coverage: 0.99 -> 0.30Improved
use psi_1 instead of psi_3additive-model estimator · Synthetic Example 3confidence interval coverage: 0.00 -> 0.92Hurt
use additive instead of linear nuisance models for psi_3psi_3 · Synthetic Example 5confidence interval coverage: 0.00 -> 0.85Improved
increase correlation between X and Z1 (delta)psi_L · Synthetic Example 1confidence interval 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