CDSP uses an effect-size asymmetry assumption and statistical power to estimate causal directions from bivariate data with uncertainty, reducing false discoveries by 18% on 100 benchmark pairs.
Misunderstandings between experimentalists and observationalists about causal inference
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
stat.ME 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Emulating stepped-wedge cluster randomized trials in the target trial emulation framework provides a conceptual structure for evaluating health policies with staggered adoption in observational and quasi-experimental studies.
Randomized experiments should be designed to predict unit-specific treatment effects, analyzing how sampling processes and models affect bias, variance, and prediction error.
citing papers explorer
-
Causal Discovery via Statistical Power (CDSP)
CDSP uses an effect-size asymmetry assumption and statistical power to estimate causal directions from bivariate data with uncertainty, reducing false discoveries by 18% on 100 benchmark pairs.
-
Emulating Stepped-Wedge Cluster Randomized Trials to Evaluate Health Policies and Interventions
Emulating stepped-wedge cluster randomized trials in the target trial emulation framework provides a conceptual structure for evaluating health policies with staggered adoption in observational and quasi-experimental studies.
-
Designing Randomized Experiments to Predict Unit-Specific Treatment Effects
Randomized experiments should be designed to predict unit-specific treatment effects, analyzing how sampling processes and models affect bias, variance, and prediction error.