A model-free variable screening method for optimal treatment regimes with high-dimensional survival data
Yang C, Cheng Y. A model-free variable screening method for optimal treatment regimes with high-dimensional survival data. Biometrika 2024, 111: 1369-1386. DOI: 10.1093/biomet/asae022.Peer-Reviewed Original ResearchHigh-dimensional survival dataOptimal treatment regimeVariable screening methodClassification problemOutcome-dependent samplingLevel of robustnessSurvival dataNonparametric learning methodKolmogorov-Smirnov approachCensoring distributionTheoretical propertiesModel misspecificationMisclassification error rateLogit lossHinge lossSimulation studyOptimal classifierBinary classificationSelection probabilityLearning methodsError rateRandom forestLung cancer datasetModel assumptionsCancer datasets
This site is protected by hCaptcha and its Privacy Policy and Terms of Service apply