AI Paper Atlas

Research map / Probabilistic and scientific modeling / Treatment effects

Data-driven Automated Negative Control Estimation (DANCE): Search for, Validation of, and Causal Inference with Negative Controls

Erich Kummerfeld, Jaewon Lim, Xu Shi

JMLR 2024 · Probabilistic and scientific modeling › Treatment effects · approach: Latent-variable causal inference · 4 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 DANCE-selected negative controls instead of random NC pairdouble-NC estimator · Simulation, complex graph (n=3000)proportion bias (%): 14.61 -> 0.18Improved
add DANCE-selected negative controls instead of random NC pairdouble-NC estimator · Simulation, simple graph (n=3000)proportion bias (%): 3.29 -> 0.01Improved
add DANCE-selected negative controls instead of random NC pairdouble-NC estimator · Simulation, complex graph (n=3000)95% CI coverage: 0.05 -> 0.94Improved
add DANCE-selected negative controls instead of random NC pairdouble-NC estimator · Simulation, simple graph (n=3000)95% CI coverage: 0.70 -> 0.96Improved
add DANCE-selected negative controls instead of random NC pairdouble-NC estimator · Simulation, complex graph, stronger edges (n=3000)95% CI coverage: 0.03 -> 0.96Improved
add DANCE-selected negative controls instead of random NC pairdouble-NC estimator · Simulation, simple graph, stronger edges (n=3000)95% CI coverage: 0.27 -> 0.96Improved
use DANCE search for NCs, which adds Monte Carlo variabilitydouble-NC estimator · Simulation, complex graph (n=1000)Monte Carlo SE (1e-3): 40.59 -> 47.46Hurt
use DANCE search for NCs, which adds Monte Carlo variabilitydouble-NC estimator · Simulation, simple graph (n=1000)Monte Carlo SE (1e-3): 21.38 -> 23.88Hurt
increase sample size from 1000 to 3000 for DANCEDANCE · Simulation, complex graphMonte Carlo SE (1e-3): 47.46 -> 28.06Improved
increase sample size to 300 or more for NC validationFindNC validation test · Simulation, simple and complex graphsROC curve: sample size 300Improved
use stronger edge strength in the simulated SEMs (ablation)DANCE · Simulation, complex graph (n=1000)proportion bias (%): -0.87 -> -0.57No clear effect
generate all variables as Bernoulli instead of Gaussian (ablation)DANCE · Simulation, binary variablesATE biasNo clear effect

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