Targeted learning with an undersmoothed LASSO propensity score model for large-scale covariate adjustment in health-care database studies
Wyss R, van der Laan M, Gruber S, Shi X, Lee H, Dutcher S, Nelson J, Toh S, Russo M, Wang S, Desai R, Lin K. Targeted learning with an undersmoothed LASSO propensity score model for large-scale covariate adjustment in health-care database studies. American Journal Of Epidemiology 2024, kwae023. PMID: 38517025, DOI: 10.1093/aje/kwae023.Peer-Reviewed Original ResearchConfounding controlLarge-scale propensity scoreDatabase studyPropensity scoreHealthcare database studiesCovariate distributionsPS modelCovariate adjustmentReduce biasData-adaptivePropensity score modelNon-overlappingEstimate treatment effectsCovariate overlapCross-fittingHealthcareTarget learningConfoundingRobust frameworkUndersmoothingCollaborative learningTreatment effectsLearningLASSOLASSO regression