2contrastlmcontrastlmGeneralContrastsofRegressionCoef2cientsDescriptionThisfunctioncomputesoneormorecontrastsoftheestimatedregressioncoef2cientsina2tfromoneofthefunctionsinDesignalongwithstandarderror ID: 885303
Download Pdf The PPT/PDF document "PackagecontrastMarch192020TitleACollecti..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
1 Package`contrast'March19,2020TitleAColle
Package`contrast'March19,2020TitleACollectionofContrastMethodsVersion0.22DescriptionOnedegreeoffreedomcontrastsforlm,glm,gls,andgeeseobjects.LicenseGPL-2URLhttps://github.com/topepo/contrastEncodingUTF-8LazyDatatrueDependsR(=2.10)Importsnlme,sandwich,rmsSuggestsknitr,kableExtra,dplyr,ggplot2,tidyr,rmarkdown,testthat,covr,geepackRoxygenNote7.0.2.9000VignetteBuilderknitrNeedsCompilationnoAuthorAlanOCallaghan[aut,cre],MaxKuhn[aut],SteveWeston[aut],JedWing[aut],JamesForester[aut],ThornThaler[aut]MaintainerAlanOCallaghan lan;.oca;llag;han@;outl;ook.;om0;RepositoryCRANDate/Publication2020-03-1914:10:02UTCRtopicsdocumented:contrast.lm.........................................2print.contrast........................................4two_factor_crossed.....................................5two_factor_incompl.....................................5Index71 2contrast.lm contrast.lmGeneralContrastsofRegressionCoefcients DescriptionThisfunctioncomputesoneo
2 rmorecontrastsoftheestimatedregressionco
rmorecontrastsoftheestimatedregressioncoefcientsinatfromoneofthefunctionsinDesign,alongwithstandarderrors,condencelimits,torZstatistics,P-values.Usage##S3methodforclass'lm'contrast(fit,...)##S3methodforclass'gls'contrast(fit,...)##S3methodforclass'lme'contrast(fit,...)##S3methodforclass'geese'contrast(fit,...)contrast_calc(fit,a,b,cnames=NULL,type=c("individual","average"),weights="equal",conf.int=0.95,fcType="simple",fcFunc=I,covType=NULL,...,env=parent.frame(2))ArgumentsfitAtofclasslm,glm,etc....Forcontrast(),thesepassargumentstocontrast_calc().Forcontrast_calc(),theyarenotused.a,bListscontainingconditionsforallpredictorsinthemodelthatwillbecontrastedtoformthehypothesisH0:a=b.Thegendatafunctionwillgeneratetheneces-sarycombinationsanddefaultvaluesforunspeciedpredictors.Seeexamplesbelow. contrast.lm3cnamesAvectorofcharacterstringsnamingthecontrastswhentype="individual".Usuallycnamesisnotnecessaryasthefunctiontriestonamethecontrastsbyexaminingwhichpredictorsarevaryingconsistentlyinthetwolists.cnamesw
3 illbeneededwhenyoucontrast"non-comparabl
illbeneededwhenyoucontrast"non-comparable"settings,e.g.,youcomparelist(treat="drug",age=c(20,30))withlist(treat="placebo",age=c(40,50).typeAcharacterstring.Settype="average"toaveragetheindividualcontrasts(e.g.,toobtaina"TypeII"or"TypeIII"contrast).weightsAnumericvector,usedwhentype="average",toobtainweightedcontrasts.conf.intThecondencelevelforcondenceintervalsforthecontrasts.fcTypeAcharacterstring:"simple","log"or"signed".fcFuncAfunctiontotransformthenumeratoranddenominatoroffoldchanges.covTypeAstringmatchingthemethodforestimatingthecovariancematrix.Thedefaultvalueproducesthetypicalestimate.Seesandwich::vcovHC()foroptions.envAnenvironmentinwhichevaluatet.DetailsThesefunctionsmirrorrms::contrast.rms()buthavefeweroptions.Therearesomebetween-packageinconsistenciesregardingdegreesoffreedominsomemodels.Seethepackagevignetteformoredetails.Foldchangesarecalculatedforeachhypothesis.WhenfcType="simple",theratiooftheagrouppredictionsoverthebgrouppredictionsareused.WhenfcType="signed",theratioisusedifitisgreaterthan1
4 ;otherwisethenegativeinverse(e.g.,-1/rat
;otherwisethenegativeinverse(e.g.,-1/ratio)isreturned.Valuealistofclasscontrast.DesigncontainingtheelementsContrast,SE,Z,var,df.residualLower,Upper,Pvalue,X,cnames,andfoldChange,whichdenotethecontrastestimates,stan-darderrors,Zort-statistics,variancematrix,residualdegreesoffreedom(thisisNULLifthemodelwasnotols),loweranduppercondencelimits,2-sidedP-value,designmatrix,andcontrastnames(orNULL).SeeAlsorms::contrast.rms(),sandwich::vcovHC()Exampleslibrary(nlme)Orthodont2OrthodontOrthodont2$newAgeOrthodont$age-11fm1Orth.lme2lme(distance~Sex*newAge,data=Orthodont2,random=~newAge|Subject)summary(fm1Orth.lme2) 4print.contrastcontrast(fm1Orth.lme2,a=list(Sex=levels(Orthodont2$Sex),newAge=8-11),b=list(Sex=levels(Orthodont2$Sex),newAge=10-11))#------------------------------------------------------------------------------anova_modellm(expression~diet*group,data=two_factor_crossed)anova(anova_model)library(ggplot2)theme_set(theme_bw()+theme(legend.position="top"))ggplot(two_factor_crossed)+aes(x=diet,y=expression,col=group,shape
5 =group)+geom_point()+geom_smooth(aes(gro
=group)+geom_point()+geom_smooth(aes(group=group),method=lm,se=FALSE)int_modellm(expression~diet*group,data=two_factor_crossed)main_effectslm(expression~diet+group,data=two_factor_crossed)#Interactioneffectisprobablyreal:anova(main_effects,int_model)#Testtreatmentinlowfatdiet:veh_grouplist(diet="lowfat",group="vehicle")trt_grouplist(diet="lowfat",group="treatment")contrast(int_model,veh_group,trt_group)#------------------------------------------------------------------------------car_modlm(mpg~am+wt,data=mtcars)print(summary(car_mod),digits=5)mean_wtmean(mtcars$wt)manual_translist(am=0,wt=mean_wt)auto_translist(am=1,wt=mean_wt)print(contrast(car_mod,manual_trans,auto_trans),digits=5) print.contrastPrintaContrastObject DescriptionPrintaContrastObjectUsage##S3methodforclass'contrast'print(x,X=FALSE,fun=function(u)u,...) two_factor_crossed5ArgumentsxResultofcontrast().XAlogical:setTRUEtoprintdesignmatrixusedincomputingthecontrasts(ortheaveragecontrast).funAfunctiontotransformthecontrast,SE,andloweranduppercondencelimi
6 tsbeforeprinting.Forexample,specifyfun=e
tsbeforeprinting.Forexample,specifyfun=exptoanti-logthemforlogisticmodels....Notused. two_factor_crossedCompleteTwo-FactorExperiment DescriptionCompleteTwo-FactorExperimentDetailsAgeneexpressionexperimentwasruntoassesstheeffectofacompoundundertwodifferentdiets:highfatandlowfat.Themaincomparisonsofinterestarethedifferencebetweenthetreatedanduntreatedgroupswithinadiet.Theinteractioneffectwasasecondaryhypothesis.Forillustration,weonlyincludetheexpressionvalueofoneofthegenes.Thestudydesignwasafulltwo-wayfactorialwithn=24samples.Valuetwo_factor_crossedAdataframeExamplestwo_factor_crossed two_factor_incomplIncompleteTwo-FactorExperimentwithRepeatedMeasurments DescriptionIncompleteTwo-FactorExperimentwithRepeatedMeasurments 6two_factor_incomplDetailsInageneexpressionexperiment,stemcellsweredifferentiatedusingasetoffactors(suchasmediatypes,cellspreadsetc.).Thesefactorswerecollapsedintoasinglecellenvironmentcongurationsvariable.Thecelllineswereassaysoverthreedays.Twoofthecongurationswereonlyrunontherstdayandtheother
7 twowereassaysatbaseline.Togetthematerial
twowereassaysatbaseline.Togetthematerials,threedonorsprovidedmaterials.Thesedonorsprovided(almost)equalrepli-cationacrossthetwoexperimentalfactors(dayandconguration).Oneofthegoalsofthisexperimentwastoassesspre-specieddifferencesinthecongurationateachtimepoint.Forexample,thedifferencesbetweencongurationsAandBatdayoneisofinterest.Also,thedifferencesbetweencongurationsCandDateachtimepointswereimportant.Sincetherearemissingcellsinthedesign,itisnotacompletetwo-wayfactorial.Onewaytoanalyzethisexperimentistofurthercollapsethetimeandcongurationdataintoasinglevariableandthenspecifyeachcomparisonusingthisfactor.Valuetwo_factor_incomplAdataframeExamplestwo_factor_incompl IndexTopicdatasetstwo_factor_crossed,5two_factor_incompl,5Topicmodelscontrast.lm,2Topicregressioncontrast.lm,2contrast.geese(contrast.lm),2contrast.gls(contrast.lm),2contrast.lm,2contrast.lme(contrast.lm),2contrast_calc(contrast.lm),2print.contrast,4rms::contrast.rms(),3sandwich::vcovHC(),3two_factor_crossed,5two_factor_incompl