2022
Predicting cumulative lead (Pb) exposure using the Super Learner algorithm
Wang X, Bakulski K, Mukherjee B, Hu H, Park S. Predicting cumulative lead (Pb) exposure using the Super Learner algorithm. Chemosphere 2022, 311: 137125. PMID: 36347347, PMCID: PMC10160242, DOI: 10.1016/j.chemosphere.2022.137125.Peer-Reviewed Original ResearchConceptsPatella leadNational Health and Nutrition Examination SurveyHealth and Nutrition Examination SurveyNutrition Examination SurveyLong-term health effectsPopulation-based studyK-shell X-ray fluorescenceNormative Aging StudyCumulative lead exposureEvaluate health effectsExamination SurveyLead concentrationsBone lead measurementsAging StudyTibia leadPositive associationStudy populationHealth effectsRegression-based predictive modelBone lead concentrationsBlood pressureFlexible machine learning approachCorrelation coefficientX-ray fluorescence techniqueLead measurements
2014
Testing departure from additivity in Tukey's model using shrinkage: application to a longitudinal setting
Ko Y, Mukherjee B, Smith J, Park S, Kardia S, Allison M, Vokonas P, Chen J, Diez‐Roux A. Testing departure from additivity in Tukey's model using shrinkage: application to a longitudinal setting. Statistics In Medicine 2014, 33: 5177-5191. PMID: 25112650, PMCID: PMC4227925, DOI: 10.1002/sim.6281.Peer-Reviewed Original ResearchMeSH KeywordsAgedAged, 80 and overAgingAtherosclerosisBone and BonesComputer SimulationEnvironmental ExposureEthnicityFemaleGene-Environment InteractionHumansIronLeadLeast-Squares AnalysisLikelihood FunctionsLongitudinal StudiesMaleMiddle AgedModels, GeneticUnited StatesUnited States Department of Veterans AffairsConceptsGene-environment interactionsMulti-Ethnic Study of AtherosclerosisModel of gene-environment interactionMulti-Ethnic StudyTukey's modelLongitudinal settingStudy of AtherosclerosisNormative Aging StudyCase-control studyIncreasing categoriesAging StudyTested interactionsLongitudinal studyCategorical variablesRobust to misspecificationInteraction termsTest departuresShrinkage estimatorsWald testInteraction estimatesIncreased powerOne-degree-of-freedom modelInteraction effectsSetsEnvironmental markers
2013
Propensity score‐based diagnostics for categorical response regression models
Boonstra P, Bondarenko I, Park S, Vokonas P, Mukherjee B. Propensity score‐based diagnostics for categorical response regression models. Statistics In Medicine 2013, 33: 455-469. PMID: 23934948, PMCID: PMC3911784, DOI: 10.1002/sim.5940.Peer-Reviewed Original ResearchConceptsRetrospective sampling designsChi-square distributionCategorical response modelsGoodness-of-fit statisticsPredicted response probabilitiesResponse regression modelsConditional distributionProportional odds modelAssess model adequacyData examplesSimulation studyVA Normative Aging StudyNormative Aging StudyPropensity scoreCumulative lead exposureOdds modelModel diagnosticsCase-control studyAssociated with diabetesBalance scoresResponse probabilityModel adequacyCohort studyAging StudyNumerical summariesNovel Likelihood Ratio Tests for Screening Gene‐Gene and Gene‐Environment Interactions With Unbalanced Repeated‐Measures Data
Ko Y, Saha‐Chaudhuri P, Park S, Vokonas P, Mukherjee B. Novel Likelihood Ratio Tests for Screening Gene‐Gene and Gene‐Environment Interactions With Unbalanced Repeated‐Measures Data. Genetic Epidemiology 2013, 37: 581-591. PMID: 23798480, PMCID: PMC4009698, DOI: 10.1002/gepi.21744.Peer-Reviewed Original ResearchConceptsGene-environment interactionsGene-gene interactionsTesting gene-gene interactionsModel gene-gene interactionsRepeated-measures studyLongitudinal cohort studyNormative Aging StudyCumulative lead exposureCase-control studyGene-environmentGene-geneType I error rateCohort studyScreening toolAging StudyLikelihood ratio testMain effectEpistasis patternsRatio testLead exposureHemochromatosis genePower propertiesPulse pressureRegression-based approachRestrictive assumptions
2010
Cumulative lead exposure and age-related hearing loss: The VA Normative Aging Study
Park S, Elmarsafawy S, Mukherjee B, Spiro A, Vokonas P, Nie H, Weisskopf M, Schwartz J, Hu H. Cumulative lead exposure and age-related hearing loss: The VA Normative Aging Study. Hearing Research 2010, 269: 48-55. PMID: 20638461, PMCID: PMC2934752, DOI: 10.1016/j.heares.2010.07.004.Peer-Reviewed Original ResearchConceptsAge-related hearing lossPure-tone averagePatella lead levelsCumulative lead exposureHearing lossHearing thresholdsNormative Aging StudyAssociated with poorer hearing thresholdsOdds of hearing lossAir conduction hearing thresholdsAssociated with hearing lossConduction hearing thresholdsPoorer hearing thresholdsAging StudyDevelopment of age-related hearing lossReduction of lead exposureVA Normative Aging StudyCross-sectional analysisLead exposureOccupational noiseHearing abilityK X-ray fluorescencePotential confoundersEpidemiological researchLead levels
2009
Graphical diagnostics to check model misspecification for the proportional odds regression model
Liu I, Mukherjee B, Suesse T, Sparrow D, Park S. Graphical diagnostics to check model misspecification for the proportional odds regression model. Statistics In Medicine 2009, 28: 412-429. PMID: 18693299, DOI: 10.1002/sim.3386.Peer-Reviewed Original ResearchConceptsCovariate effectsOrdinal responsesModel misspecificationProportional odds regression modelStudy covariate effectsGoodness-of-fit statisticsClass of modelsNumerical methodFunctional misspecificationBinary responsesGraphical diagnosticsSimulation studyCumulative logitsMisspecificationCumulative sumRegression modelsGraphical methodSumArbogastVA Normative Aging StudyCovariatesProportional odds regressionClass