Nonparametric identification is not enough, but randomized controlled trials are
Aronow P, Robins J, Saarinen T, Sävje F, Sekhon J. Nonparametric identification is not enough, but randomized controlled trials are. Observational Studies 2025, 11: 3-16. PMID: 40487083, PMCID: PMC12139723, DOI: 10.1353/obs.2025.a956837.Peer-Reviewed Original ResearchPropensity score functionResults of RobinsValid confidence intervalsAverage treatment effectParametric rateScoring functionContinuous confoundersNonparametric identificationUnconfoundedness assumptionBinary outcomesStatistical estimationObservational settingPropensity scoreAssumptionsEstimationConfidence intervalsPropensityRobinTreatment effectsFunctionInferenceRejoinder: Nonparametric identification is not enough, but randomized controlled trials are.
Aronow P, Robins J, Saarinen T, Sävje F, Sekhon J. Rejoinder: Nonparametric identification is not enough, but randomized controlled trials are. Observational Studies 2025, 11: 85-90. PMID: 40487084, PMCID: PMC12139717, DOI: 10.1353/obs.2025.a956844.Peer-Reviewed Original ResearchRoot-nPropensity score functionRoot-n rateConditional expectation functionFinite-sampleContinuous covariatesNonparametric identificationExpectation functionUntestable assumptionsRandomized experimentScoring functionPotential outcomesEstimated averageSample sizeEstimationPropensity scoreConfidence intervalsPropensityAssumptionsCovariatesFunctionUniformityRemarks
This site is protected by hCaptcha and its Privacy Policy and Terms of Service apply