2023
Mediation analysis in the presence of continuous exposure measurement error
Cheng C, Spiegelman D, Li F. Mediation analysis in the presence of continuous exposure measurement error. Statistics In Medicine 2023, 42: 1669-1686. PMID: 36869626, PMCID: PMC11320713, DOI: 10.1002/sim.9693.Peer-Reviewed Original ResearchConceptsBody mass indexExposure measurement errorPhysical activityMediation proportionHealth Professionals FollowCardiovascular disease incidenceProfessionals FollowMediation analysisMass indexCardiovascular diseaseLower riskStudy designEffect estimatesValidation study designContinuous exposureBiased effect estimatesTrue exposureMediatorsExposureValidation studyBinary outcomesHealth science studiesOutcomesRiskDisease incidence
2021
A Bayesian approach for estimating the partial potential impact fraction with exposure measurement error under a main study/internal validation design
Chen X, Chang J, Spiegelman D, Li F. A Bayesian approach for estimating the partial potential impact fraction with exposure measurement error under a main study/internal validation design. Statistical Methods In Medical Research 2021, 31: 404-418. PMID: 34841964, DOI: 10.1177/09622802211060514.Peer-Reviewed Original ResearchConceptsPotential impact fractionImpact fractionExposure measurement errorHealth professionalsStudy designColorectal cancer incidenceValidation study designBurden of diseaseRisk factorsCancer incidenceHealth StudyDisease casesPublic health studiesRed meatContinuous exposureExposureProfessionalsIncidenceReclassification approachValidation designDiseaseIntake
2020
Estimation and inference for the population attributable risk in the presence of misclassification
Wong BHW, Lee J, Spiegelman D, Wang M. Estimation and inference for the population attributable risk in the presence of misclassification. Biostatistics 2020, 22: 805-818. PMID: 32112073, PMCID: PMC8966954, DOI: 10.1093/biostatistics/kxz067.Peer-Reviewed Original ResearchConceptsPopulation attributable riskAttributable riskPartial population attributable riskHigh red meat intakeColorectal cancer incidenceRed meat intakeAlcohol intakeRisk factorsCancer incidenceMeat intakeEpidemiologic studiesPublic health researchDisease casesStudy designValidation study designInternal validation studyHealth researchTarget populationIntakeValidation studyRiskHealth evaluation methodPresence of misclassificationIncidenceDisease
1997
Fully parametric and semi-parametric regression models for common events with covariate measurement error in main study/validation study designs.
Spiegelman D, Casella M. Fully parametric and semi-parametric regression models for common events with covariate measurement error in main study/validation study designs. Biometrics 1997, 53: 395-409. PMID: 9192443, DOI: 10.2307/2533945.Peer-Reviewed Original ResearchConceptsMain study/validation study designsSemi-parametric methodMeasurement error modelSemi-parametric estimatesCovariate measurement errorSemi-parametric regression modelEmpirical considerationsTrading efficiencyError modelInference proceedsConvenient mathematical propertiesMeasurement errorLikelihood functionModel choiceJoint likelihood functionValidation study designMisspecificationStandard theoryNonparametric formFamily of modelsImportant biasParametric resultsModel covariatesRegression modelsChoice