sas af
Paper261-27
HowtoUseSAS forLogisticRegressionwithCorrelatedDataOliver Kuss, Institute of Medical Epidemiology, Biostatistics, and Informatics,
Halle/Saale,Germany
ABSTRACT
Manystudydesignsinappliedsciencesgiverisetocorrelateddata.Forexample,subjectsarefollowedovertime,arerepeatedlytreatedunderdifferentexperimentalconditions,orareobservedinlogicalunits(e.g.clinics,families,litters).
StatisticalmethodsforregressionanalysisforthiskindofdatawithcontinuousresponsesarequiteestablishedandtheSAS systemoffersavarietyofprocedures(GLMprocedure,MIXEDprocedure)foranalysis.Fordiscreteresponses,however,wehavetofaceagreatermathematicalcomplexityandstatisticalanalysisisnotthatstraightforwardanylonger.
WeshowthedifferentoptionsthattheSAS systemoffersfortheanalysisofbinaryresponseswithcorrelateddata(GENMODprocedure,%GLIMMIX,%NLINMIX,NLMIXEDprocedure,PHREG/LOGISTICprocedureandMeta-Analyticmethods),investigatetheirstatisticalproperties,andillustratethembyanexampleofamulticenterstudy.
Weconcludethatitisdifficulttogivegeneralrecommendationswhichofthemethodstousebecausethisdependsonthedataathandandonthedesiredinterpretationofparameters,butinourdatasetwefeelmostcomfortablewiththeresultsfromtheNLMIXEDandthePHREG/LOGISTICprocedure.
INTRODUCTION
Thelogisticregressionmodelhasbecomethestandardanalyzingtoolforbinaryresponsesinavarietyofdisciplines.Reasonsforthisare:easeofinterpretationofparametersasadjustedoddsratios,possibilityofcalculatingprognosesfortheeventofinterest,andavailabilityofstandardsoftware.TheLOGISTICprocedureisthestandardtoolinSAS softwareforfittinglogisticregressionmodels,butsolutionswiththeGENMOD,thePROBIT,ortheCATMODprocedurearealsopossible.
Acrucialpointinstandardlogisticregressionanalysisisthatobservationsareindependentofoneanotheranditisknownthatviolationsofthisassumptionresultininvalidstatisticalinference.However,manystudydesignsinappliedsciencesgiverisetocorrelateddata.Forexample,subjectsarefollowedovertimeandresponsesareassessedatdifferenttimepoints,arerepeatedlytreatedunderdifferentexperimentalconditions,orareobservedinlogicalunits(e.g.clinics,families,litters).
InthefollowingweillustratethedifferentoptionsthatSAS softwareoffersfortheanalysisofbinaryresponseswithcorrelateddata(GENMODprocedure,%GLIMMIX,%NLINMIX,NLMIXED
procedure).Weshowthateachofthemestimatesparametersfromoneoftwodifferentstatisticalmodelsandcommentontheinterpretationofparametersandthestatisticalpropertiesofthemethodsinvolved.Themodelsandtheestimationproceduresareillustratedbyanexampleofamulticenterrandomizedcontrolledclinicaltrial.
THEDATA
ThedatasetthatweusetoexplainthevariousprocedureswasoriginallyreportedbyBeitler/Landis,1985,andwasalsousedbyWolfinger,1999,tointroducethenewNLMIXEDprocedure.Thedatahavebeencollectedinamulticenterrandomizedcontrolledclinicaltrialconductedineightdifferentclinics.Thepurposeofthestudywastoassesstheeffectofatopicalcreamtreatment
comparedtonotreatmentoncuringnonspecificinfections.Ineachoftheeightclinics(clinic),thenumberoftreated(n)andthe
numberofsuccessfullycuredpersons(x)wererecordedfor
treatment(treatment=1)andcontrol(treatment=0).TheSAS datasetisthefollowing:
datainfection;
inputclinictreatmentxn;datalines;111136101037211620202232311419307194121640117516175001261111600107115701981468067
run;
ACRUDEANALYSIS
Afirstpreliminaryanalysistoassessthetreatmenteffectwillmaybeignorethefactthatthedatawereobservedindifferentclinicsandcollapsethedatainasingle2x2-table.AsuitablemeasurefortreatmenteffectinthiscaseistheoddsratioandtheFREQ
procedurecanbeusedtoachieveanestimator.Somesmalldatamanipulation(actuallywritingeachpersonwithitsresponse(cure)inasingleline)hastoprecedetheanalysis(thevariablestatuswillbeneededinalateranalysis):
datainfection2(drop=i);
setinfection;doi=1ton;
ifi<=xthencure=1;ifi>xthencure=0;status=2-cure;output;end;
run;
procfreqdata=infection2;
tablestreatment*cure/relrisk;
run;
Thisanalysisyieldsanestimatedoddsratio[with95%-CI]of1.498[0.915;2.452],thatmeanstheoddsforcuringtheinfectionis
roughly50%higherinthetreatmentcomparedtothecontrolgroup.However,

proceedingthiswaycompletelyignoresthefactthatthestudywasundertakeninseveralclinicsandwemightsuspectthatdifferentfeaturesofthem(personnel,environment,typicalpopulationofpatients)mightinfluencethetreatmenteffectintheindividual
clinic.Notethatthisalsoimpliesthatthereisacorrelationofpatientswithinindividualclinics.Inaclinicwithhightreatmenteffectmanypatientswillbecuredandacureinasinglepatientwillbe
accompaniedwithahigherprobabilitybyacureofanotherpatientfromthesameclinic.
How to Display Correlated ROC Curves with the SAS System_天文/地理_自然科学...PROC LOGISTIC DATA= input- SAS-data-set ; Posters MODEL status = test /...
Ch16 Logistic regression Logist 回归_医学_高等教育...data independent observation correlated observation ...If one really wishes to use for prediction, the...
SAS Logistic Regression Introduction Probability, Odds, and Odds Ratios Logistic Regression ROC Curves SAS> DATA LOGISTIC; SAS> SAS> Set Accident; SAS> ...
2009. Linear Regression Models for Panel Data ...how to estimate each model using SAS 9.2, ...ui is allowed to be correlated to other regressors...
A Tutorial on Logistic Regression Ying So, SAS ...Scatterplot of Sample Points in DATA2 with ...it is more convenient to use PROC PHREG (see ...
本研究的数据预处理采用 SAS9.2 软件,多水平模型...data sets is that observations are correlated.That...with multilevel logistic regression models, including...
To use SAS, you write SAS programs that ...However, SAS can work with many data files at ...logistic regression (because these commands are ...
Data Mining SEMMA Methodology (SAS) ? Sample ...Solution: Use logistic regression, neural nets to...characteristics strong correlated with fraud 9 Risk...
A major statistical problem with cluster-correlated data arises from ...(1995) for logistic regression in teratology studies, and by Williams (1995...
how to estimate individual models using SAS 9.1...Regression Logistic regression Probit Plum Plum ...identically distributed” errors are correlated (Greene...
热门文档