AI Paper Atlas

Research map / Probabilistic and scientific modeling / Treatment effects

Double Machine Learning Density Estimation for Local Treatment Effects with Instruments

Yonghan Jung, Jin Tian, Elias Bareinboim

NeurIPS 2021 · Probabilistic and scientific modeling › Treatment effects · approach: Benchmarking treatment effect models · 3 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
use the debiased KLTE estimator instead of the plug-in kernel-smoothing estimatorkernel-smoothing LTE density estimation · Synthetic mixture of four Gaussiansrecovery of density modes (qualitative)Improved
use the MLTE estimator instead of the moment-score estimatormodel-based LTE density estimation with normal density class · Synthetic mixture of four Gaussiansrecovery of density shape (qualitative)No clear effect
use kernel-based KLTE instead of normal-model-based estimators when the density class is misspecifiedLTE density estimation · Synthetic mixture of four Gaussianscapture of multimodality (qualitative)Improved
use MLTE and KLTE (proposed debiased estimators) versus Moment and plug-in kernel-smoothing401(k) participation effect on net financial assets · 401(k) data, 9275 individualsestimated LTE density shape (qualitative)No clear effect
convert KLTE density estimate into a CDFKLTE on 401(k) data · 401(k) dataconsistency with prior CDF-based analyses (qualitative)Improved

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