Package breakpoint July Type Package Title An R Package for Multiple BreakPoint Detection via the CrossEntropy Method Version - Description

0 Date 20140114 Author Priyadarshana WJRM and Georgy Sofronov Maintainer Priyadarshana WJRM Description Implements the crossentropy CE method which is a model based stochastic optimization tech nique to estimate both the number as well as the corresp ID: 22640 Download Pdf

Similar presentations

Package fun July Type Package Title Use R for Fun Version
Package fun July Type Package Title Use R for Fun Version

10 Date 20110812 Author Yihui Xie Taiyun Wei and Yixuan Qiu Maintainer Yihui Xie Description This is a collection of R games and other funny stuffsuch as the classi cal Mine sweeper and sliding puzzles License GPL LazyLoad yes URL httpsgithubcomyihui

Package aspect July Type Package Title Aspects of Multivariables Version
Package aspect July Type Package Title Aspects of Multivariables Version

02 Date 20101130 Author Jan de Leeuw Kurt Hornik Patrick Mair Maintainer Jan de Leeuw Description This package consists of two main functions The 64257rst function is corAspect per forms optimal scaling by maximizing an aspect ie a target function su

Package quadprog July Type Package Title Functions to solve Quadratic Programming Problems
Package quadprog July Type Package Title Functions to solve Quadratic Programming Problems

Version 155 Date 20130417 Author S original by Berwin A Turlach port by Andreas Weingessel Maintainer Berwin A Turlach Description This package contains routines and documentation for solving quadratic programming problems Depends R 2150 License GP

Package functional July Type Package Title Curry Compose and other higherorder functions Version
Package functional July Type Package Title Curry Compose and other higherorder functions Version

6 Date 20140715 Author Peter Danenberg Maintainer Peter Danenberg Description Curry Compose and other higherorder functions License GPL 2 LazyLoad yes NeedsCompilation no Repository CRAN DatePublication 20140716 073804 topics documented Compose

Package surface July Type Package Title Fitting Hansen Models to Investigate Convergent Evolution Version
Package surface July Type Package Title Fitting Hansen Models to Investigate Convergent Evolution Version

41 Date 20140214 Author Travis Ingram Maintainer Travis Ingram Depends R 26 ape ouch MASS geiger Suggests igraph Description SURFACE is a datadriven phylogenetic comparative method for 64257tting stabilizing selec tion models to continuous trait dat

Package Exact July Type Package Title Unconditional Exact Test Version
Package Exact July Type Package Title Unconditional Exact Test Version

4 Date 20130721 Author Peter Calhoun Maintainer Peter Calhoun Description Unconditional exact tests for 2x2 contingency tables License GPL2 NeedsCompilation no Repository CRAN DatePublication 20130722 073404 topics documented Exact

Package depth July Type Package Title Depth functions tools for multivariate analysis Version
Package depth July Type Package Title Depth functions tools for multivariate analysis Version

00 Date 20120812 Author Maxime Genest JeanClaude Masse JeanFrancois Plante Maintainer JeanFrancois Plante Description Depth functions methodology applied to multivariate analysis Besides allowing calculation of depth values and depthbased location

Package moments July Type Package Title Moments cumulants skewness kurtosis and related tests Version
Package moments July Type Package Title Moments cumulants skewness kurtosis and related tests Version

13 Date 20120124 Author Lukasz Komsta Frederick Novomestky Maintainer Lukasz Komsta Description Functions to calculate moments Pearsons kurtosisGearys kurtosis and skew ness tests related to them AnscombeGlynn DAgostino BonettSeier License GPL 2 UR

Package sos July Title Search contributed R packages sort by package Version
Package sos July Title Search contributed R packages sort by package Version

38 Author Spencer Graves Sundar DoraiRaj and Romain Francois Maintainer Spencer Graves Description Search contributed R packages sort by package License GPL 2 Depends brew Suggests RODBC WriteXLS fda Repository CRAN RepositoryRForgeProject rsitesear

Package Storm February Type Package Version
Package Storm February Type Package Version

2 Date 20141225 Title Write Storm Bolts in R using the Storm MultiLanguage Protocol Author Allen Day Maintainer Allen Day License GPL 2 LazyLoad yes Depends R 210 methods permute rjson Description Storm is a distributed realtime computation system

288K - views

Package breakpoint July Type Package Title An R Package for Multiple BreakPoint Detection via the CrossEntropy Method Version

Published bycalandra-battersby

0 Date 20140114 Author Priyadarshana WJRM and Georgy Sofronov Maintainer Priyadarshana WJRM Description Implements the crossentropy CE method which is a model based stochastic optimization tech nique to estimate both the number as well as the corresp

Tags : Date 20140114 Author Priyadarshana
Embed :
Pdf Download Link

Download Pdf - The PPT/PDF document "Package breakpoint July Type Package T..." 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.

Package breakpoint July Type Package Title An R Package for Multiple BreakPoint Detection via the CrossEntropy Method Version






Presentation on theme: "Package breakpoint July Type Package Title An R Package for Multiple BreakPoint Detection via the CrossEntropy Method Version"— Presentation transcript:

2breakpoint-packageIndex25 breakpoint-packageMultipleBreak-PointDetectionviatheCross-EntropyMethod DescriptionThebreakpointpackageimplementsvariantsoftheCross-Entropy(CE)methodproposedinPriyadar-shanaandSofronov(2015,2012aand2012b)toestimateboththenumberandthecorrespondinglocationsofbreak-pointsinbiologicalsequencesofcontinuousanddiscretemeasurements.Theproposedmethodprimarilybuilttodetectmultiplebreak-pointsingenomicsequences.However,itcanbeeasilyextendedandappliedtootherproblems.DetailsPackage:breakpointType:PackageVersion:1.2Date:2016-01-11License:GPL2.0"breakpoint""packageprovidesestimatesonboththenumberaswellasthecorrespondinglocationsofbreak-points.ThealgorithmsutilizetheCross-Entropy(CE)method,whichisamodel-basedstochasticoptimizationproceduretoobtaintheestimatesonlocations.Modelselectionproceduresareusedtoobtainthenumberofbreak-points.Currentimplementationofthemethodologyworksasanexactsearchmethodinestimatingthenumberofbreak-points.However,itsupportscalculationsiftheinitiallocationsareprovided.Aparallelimplementationoftheprocedurescanbecarried-outinUnix/Linux/MACOSXandWINDOWSOSwiththeuseof"parallel"and"doParallel"packages.Author(s)Priyadarshana,W.J.R.M.andSofronov,G.Maintainer:Priyadarshana,W.J.R.M.w&#xmjay;ꅐardana@swin.edu.auReferencesPriyadarshana,W.J.R.M.,SofronovG.(2015).MultipleBreak-PointsDetectioninArrayCGHDataviatheCross-EntropyMethod,IEEE/ACMTransactionsonComputationalBiologyandBioin-formatics,12(2),pp.487-498.Priyadarshana,W.J.R.M.andSofronov,G.(2012a).AModiedCross-EntropyMethodforDetectingMultipleChange-PointsinDNACountData.InProc.oftheIEEEConferenceonEvo-lutionaryComputation(CEC),1020-1027,DOI:10.1109/CEC.2012.6256470.Priyadarshana,W.J.R.M.andSofronov,G.(2012b).TheCross-EntropyMethodandMultipleChange-PointsDetectioninZero-InatedDNAreadcountdata.In:Y.T.Gu,S.C.Saha(Eds.)The 4CE.NBpenaltyUsercanselecteitherBICorAICtoobtainthenumberofbreak-points.Options:"BIC","AIC".Defaultis"BIC".parallelAlogicalargumentspecifyingifparallelcomputationshouldbecarried-out(TRUE)ornot(FALSE).Bydefaultitissetas`FALSE'.InWINDOWSOSsystems"snow"functionalitiesareused,whereasinUnix/Linux/MACOSX"multicore"functionalitiesareusedtocarryoutparallelcomputationswiththemaximumnumberofcoresavailable.DetailsThenegativebinomial(NB)distributionisusedtomodelthediscrete(count)data.NBmodelispre-ferredoverthePoissionmodelwhenover-dispersionisobservedinthecountdata.Aperformancefunctionscore(BICorAIC)iscalculatedforeachofthesolutionsgeneratedbythestatisticaldistri-bution(fourparameterbetadistributionortruncatednormaldistribution),whichisusedtosimulatebreak-pointsfromnobreak-pointtotheuserprovidedmaximumnumberofbreak-points(defaultis10).ThesolutionthatminimizestheBIC/AICwithrespecttothenumberofbreak-pointsisre-portedastheoptimalsolution.Finally,alistcontainingavectorofbreak-pointlocations,numberofbreak-points,BIC/AICvaluesandlog-likelihoodvalueisreturnedintheconsole.ValueAlistisreturnedwithfollowingitems:No.BPsThenumberofbreak-pointsinthedatathatisestimatedbytheCEmethodBP.LocAvectorofbreak-pointlocationsBIC/AICBIC/AICvaluellLoglikelihoodoftheoptimalsolutionAuthor(s)Priyadarshana,W.J.R.M.w&#xmjay;ꅐardana@swin.edu.auReferencesPriyadarshana,W.J.R.M.andSofronov,G.(2012a)AModiedCross-EntropyMethodforDetect-ingMultipleChange-PointsinDNACountData,InProc.oftheIEEEConferenceonEvolutionaryComputation(CEC),1020-1027,DOI:10.1109/CEC.2012.6256470.Priyadarshana,W.J.R.M.andSofronov,G.(2012b)TheCross-EntropyMethodandMultipleChange-PointsDetectioninZero-InatedDNAreadcountdata,In:Y.T.Gu,S.C.Saha(Eds.)The4thInternationalConferenceonComputationalMethods(ICCM2012),1-8,ISBN978-1-921897-54-2.Rubinstein,R.,andKroese,D.(2004)TheCross-EntropyMethod:AUniedApproachtoCom-binatorialOptimization,Monte-CarloSimulationandMachineLearning.Springer-Verlag,NewYork.Schwarz,G.(1978)Estimatingthedimensionofamodel,TheAnnalsofStatistics,6(2),461-464. 6CE.NB.InitUsageCE.NB.Init(data,init.locs,eps=0.01,rho=0.05,M=200,h=5,a=0.8,b=0.8,distyp=1,penalty="BIC",var.init=1e+05,parallel=FALSE)Argumentsdatadatatobeanalysed.Asinglecolumnarrayoradataframe.init.locsInitialbreak-pointlocations.epsthecut-offvalueforthestoppingcriterionintheCEmethod.Defaultvalueis0.01.rhothefractionwhichisusedtoobtainthebestperformingsetofsamplesolutions(i.e.,elitesample).Defaultvalueis0.05.Msamplesizetobeusedinsimulatingthelocationsofbreak-points.Defaultvalueis200.hminimumaberrationwidth.Defaultis5.aasmoothingparametervalue.Itisusedinthefourparameterbetadistributiontosmoothbothshapeparameters.Whensimulatingfromthetruncatednormaldis-tribution,thisvalueisusedtosmooththeestimatesofthemeanvalues.Defaultis0.8.basmoothingparametervalue.Itisusedinthetruncatednormaldistributiontosmooththeestimatesofthestandarddeviation.Defaultis0.8.distypdistributiontosimulatebreak-pointlocations.Options:1=fourparameterbetadistribution,2=truncatednormaldistribution.Defaultis1.penaltyUsercanselecteitherBICorAICtoobtainthenumberofbreak-points.Options:"BIC","AIC".Defaultis"BIC".var.initInitialvariancevaluetofacilitatethesearchprocess.Defaultis100000.parallelAlogicalargumentspecifyingifparallelcomputationshouldbecarried-out(TRUE)ornot(FALSE).Bydefaultitissetas`FALSE'.InWINDOWSOSsystems"snow"functionalitiesareused,whereasinUnix/Linux/MACOSX"multicore"functionalitiesareusedtocarryoutparallelcomputationswiththemaximumnumberofcoresavailable.DetailsThenegativebinomial(NB)distributionisusedtomodelthediscrete(count)data.NBmodelispre-ferredoverthePoissionmodelwhenover-dispersionisobservedinthecountdata.Aperformancefunctionscore(BICorAIC)iscalculatedforeachofthesolutionsgeneratedbythestatisticaldis-tribution(fourparameterbetadistributionortruncatednormaldistribution)withrespecttotheuserprovidedinitiallocations.Finally,alistcontainingavectorofbreak-pointlocations,numberofbreak-points,BIC/AICvaluesandlog-likelihoodvalueisreturnedintheconsole.ValueAlistisreturnedwithfollowingitems:No.BPsThenumberofbreak-points CE.Normal.Init.Mean9aasmoothingparametervalue.Itisusedinthefourparameterbetadistributiontosmoothbothshapeparameters.Whensimulatingfromthetruncatednormaldis-tribution,thisvalueisusedtosmooththeestimatesofthemeanvalues.Defaultis0.8.basmoothingparametervalue.Itisusedinthetruncatednormaldistributiontosmooththeestimatesofthestandarddeviation.Defaultis0.8.distypdistributiontosimulatebreak-pointlocations.Options:1=fourparameterbetadistribution,2=truncatednormaldistribution.Defaultis1.penaltyUsercanselectfrommBIC,BICorAICtoobtaintheoptimalnumberofbreak-points.Options:"mBIC","BIC"and"AIC".Defaultis"mBIC".var.initInitialvariancevaluetofacilitatethesearchprocess.Defaultis100000.parallelAlogicalargumentspecifyingifparallelcomputationshouldbecarried-out(TRUE)ornot(FALSE).Bydefaultitissetas`FALSE'.InWINDOWSOSsystems"snow"functionalitiesareused,whereasinUnix/Linux/MACOSX"multicore"functionalitiesareusedtocarryoutparallelcomputationswiththemaximumnumberofcoresavailable.DetailsThenormaldistributionisusedtomodelthecontinuousdata.Aperformancefunctionscore(mBIC/BIC/AIC)iscalculatedforeachofthesolutionsgeneratedbythestatisticaldistribution(fourparameterbetadistributionortruncatednormaldistribution),whichisusedtosimulatebreak-pointsfromtheuserprovidedinitiallocations.Thesolutionthatmaximizestheselectioncriteriawithre-specttothenumberofbreak-pointsisreportedastheoptimalsolution.Finally,alistcontainingavectorofbreak-pointlocations,numberofbreak-points,mBIC/BIC/AICvaluesandlog-likelihoodvalueisreturnedintheconsole.ValueAlistisreturnedwithfollowingitems:No.BPsThenumberofbreak-pointsBP.LocAvectorofbreak-pointlocationsmBIC/BIC/AICmBIC/BIC/AICvaluellLoglikelihoodoftheoptimalsolutionAuthor(s)Priyadarshana,W.J.R.M.w&#xmjay;ꅐardana@swin.edu.auReferencesPriyadarshana,W.J.R.M.,SofronovG.(2015).MultipleBreak-PointsDetectioninArrayCGHDataviatheCross-EntropyMethod,IEEE/ACMTransactionsonComputationalBiologyandBioin-formatics,12(2),pp.487-498.Priyadarshana,W.J.R.M.andSofronov,G.(2012)AModiedCross-EntropyMethodforDetect-ingMultipleChange-PointsinDNACountData,InProc.oftheIEEEConferenceonEvolutionaryComputation(CEC),1020-1027,DOI:10.1109/CEC.2012.6256470. CE.Normal.Init.MeanVar11Argumentsdatadatatobeanalysed.Asinglecolumnarrayoradataframe.init.locsInitialbreak-pointlocations.epsthecut-offvalueforthestoppingcriterionintheCEmethod.Defaultvalueis0.01.rhothefractionwhichisusedtoobtainthebestperformingsetofsamplesolutions(i.e.,elitesample).Defaultvalueis0.05.Msamplesizetobeusedinsimulatingthelocationsofbreak-points.Defaultvalueis200.hminimumaberrationwidth.Defaultis5.aasmoothingparametervalue.Itisusedinthefourparameterbetadistributiontosmoothbothshapeparameters.Whensimulatingfromthetruncatednormaldis-tribution,thisvalueisusedtosmooththeestimatesofthemeanvalues.Defaultis0.8.basmoothingparametervalue.Itisusedinthetruncatednormaldistributiontosmooththeestimatesofthestandarddeviation.Defaultis0.8.distypdistributiontosimulatebreak-pointlocations.Options:1=fourparameterbetadistribution,2=truncatednormaldistribution.Defaultis1.penaltyUsercanselecteitherfromBICorAICtoobtaintheoptimalnumberofbreak-points.Options:"BIC"and"AIC".Defaultis"BIC".var.initInitialvariancevaluetofacilitatethesearchprocess.Defaultis100000.parallelAlogicalargumentspecifyingifparallelcomputationshouldbecarried-out(TRUE)ornot(FALSE).Bydefaultitissetas`FALSE'.InWINDOWSOSsystems"snow"functionalitiesareused,whereasinUnix/Linux/MACOSX"multicore"functionalitiesareusedtocarryoutparallelcomputationswiththemaximumnumberofcoresavailable.DetailsThenormaldistributionisusedtomodelthecontinuousdata.Aperformancefunctionscore(BIC/AIC)iscalculatedforeachofthesolutionsgeneratedbythestatisticaldistribution(fourpa-rameterbetadistributionortruncatednormaldistribution),whichisusedtosimulatebreak-pointsfromtheuserprovidedinitiallocations.Changesinbothmeanandvariancesareestimated.Thesolutionthatmaximizestheselectioncriteriawithrespecttothenumberofbreak-pointsisreportedastheoptimalsolution.Finally,alistcontainingavectorofbreak-pointlocations,numberofbreak-points,BIC/AICvaluesandlog-likelihoodvalueisreturnedintheconsole.ValueAlistisreturnedwithfollowingitems:No.BPsThenumberofbreak-pointsBP.LocAvectorofbreak-pointlocationsBIC/AICBIC/AICvaluellLoglikelihoodoftheoptimalsolution CE.Normal.Mean13 CE.Normal.MeanMultipleBreak-pointDetectionviatheCEMethodforContinuousData(Meanlevels) DescriptionThisfunctionperformscalculationstoestimateboththenumberofbreak-pointsandtheircorre-spondinglocationsofcontinuousmeasurementswiththeCEmethod.Thenormaldistributionisusedtomodeltheobservedcontinousdata.Accrossthesegmentsstandarddeviationisassumedtobethesame.Thisfunctionsupportsforthesimulationofbreak-pointlocationsbasedonthefourparameterbetadistributionortruncatednormaldistribution.UsercanselectfromthemodiedBIC(mBIC)proposedbyZhangandSiegmund(2007),BICorAICtoobtaintheoptimalnumberofbreak-points.UsageCE.Normal.Mean(data,Nmax=10,eps=0.01,rho=0.05,M=200,h=5,a=0.8,b=0.8,distyp=1,penalty="mBIC",parallel=FALSE)Argumentsdatadatatobeanalysed.Asinglecolumnarrayoradataframe.Nmaxmaximumnumberofbreak-points.Defaultvalueis10.epsthecut-offvalueforthestoppingcriterionintheCEmethod.Defaultvalueis0.01.rhothefractionwhichisusedtoobtainthebestperformingsetofsamplesolutions(i.e.,elitesample).Defaultvalueis0.05.Msamplesizetobeusedinsimulatingthelocationsofbreak-points.Defaultvalueis200.hminimumaberrationwidth.Defaultis5.aasmoothingparametervalue.Itisusedinthefourparameterbetadistributiontosmoothbothshapeparameters.Whensimulatingfromthetruncatednormaldis-tribution,thisvalueisusedtosmooththeestimatesofthemeanvalues.Defaultis0.8.basmoothingparametervalue.Itisusedinthetruncatednormaldistributiontosmooththeestimatesofthestandarddeviation.Defaultis0.8.distypdistributionstosimulatebreak-pointlocations.Options:1=fourparameterbetadistribution,2=truncatednormaldistribution.Defaultis1.penaltyUsercanselectfrommBIC,BICorAICtoobtaintheoptimalnumberofbreak-points.Options:"mBIC","BIC"and"AIC".Defaultis"mBIC".parallelAlogicalargumentspecifyingifparallelcomputationshouldbecarried-out(TRUE)ornot(FALSE).Bydefaultitissetas`FALSE'.InWINDOWSOSsystems"snow"functionalitiesareused,whereasinUnix/Linux/MACOSX"multicore"functionalitiesareusedtocarryoutparallelcomputationswiththemaximumnumberofcoresavailable. CE.Normal.MeanVar15Examplesdata(ch1.GM03563)##Notrun:##CEwithfourparameterbetadistributionwithmBICastheselectioncriterion##obj1CE.Normal.Mean(ch1.GM03563,distyp=1,penalty="mBIC",parallel=TRUE)profilePlot(obj1,simdata)##CEwithtruncatednormaldistributionwithmBICastheselectioncriterion##obj2CE.Normal.Mean(ch1.GM03563,distyp=2,penalty="mBIC",parallel=TRUE)profilePlot(obj2,simdata)##End(Notrun) CE.Normal.MeanVarMultiplebreak-pointdetectionviatheCEmethodforcontinuousdata(bothmeanandvariancechanges) DescriptionThisfunctionperformscalculationstoestimateboththenumberofbreak-pointsandtheircorre-spondinglocationsofcontinuousmeasurementswiththeCEmethod.Thenormaldistributionisusedtomodeltheobservedcontinousdata.Thisfunctionsupportsforthesimulationofbreak-pointlocationsbasedonthefourparameterbetadistributionortruncatednormaldistribution.UsercanselecteitherfromthegenralBICorAICtoobtaintheoptimalnumberofbreak-points.UsageCE.Normal.MeanVar(data,Nmax=10,eps=0.01,rho=0.05,M=200,h=5,a=0.8,b=0.8,distyp=1,penalty="BIC",parallel=FALSE)Argumentsdatadatatobeanalysed.Asinglecolumnarrayoradataframe.Nmaxmaximumnumberofbreak-points.Defaultvalueis10.epsthecut-offvalueforthestoppingcriterionintheCEmethod.Defaultvalueis0.01.rhothefractionwhichisusedtoobtainthebestperformingsetofsamplesolutions(i.e.,elitesample).Defaultvalueis0.05.Msamplesizetobeusedinsimulatingthelocationsofbreak-points.Defaultvalueis200.hminimumaberrationwidth.Defaultis5.aasmoothingparametervalue.Itisusedinthefourparameterbetadistributiontosmoothbothshapeparameters.Whensimulatingfromthetruncatednormaldis-tribution,thisvalueisusedtosmooththeestimatesofthemeanvalues.Defaultis0.8. CE.ZINB17Zhang,N.R.,andSiegmund,D.O.(2007)AmodiedBayesinformationcriterionwithapplicationstotheanalysisofcomparativegenomichybridizationdata.Biometrics,63,22-32.SeeAlsoCE.Normal.Init.MeanforCEwithnormalwithinitiallocations,CE.Normal.MeanforCEwithnormaltodetectbreak-pointsinmeanlevels,CE.Normal.Init.MeanVarforCEwithnormaltodetectbreak-pointsinbothmeanandvariancewithinitiallocations,profilePlottoobtainmeanproleplot.Examples##Notrun:simdataas.data.frame(c(rnorm(200,100,5),rnorm(1000,160,8),rnorm(300,120,10)))##CEwithfourparameterbetadistributionwithBICastheselectioncriterion##obj1CE.Normal.MeanVar(simdata,distyp=1,penalty="BIC",parallel=TRUE)profilePlot(obj1,simdata)##CEwithtruncatednormaldistributionwithBICastheselectioncriterion##obj2CE.Normal.MeanVar(simdata,distyp=2,penalty="BIC",parallel=TRUE)profilePlot(obj2,simdata)##End(Notrun) CE.ZINBMultipleBreak-pointDetectionviatheCEMethodwithZero-InatedNegativeBinomialDistribution DescriptionPerformscalculationstoestimateboththenumberofbreak-pointsandtheircorrespondinglocationsofdiscretemeasurementswiththeCEmethod.Zero-inatednegativebinomialdistributionisusedtomodeltheexcesszeroobservationsandtomodelover-dispersesionintheoberveddiscrete(count)data.Thisfunctionsupportsforthesimulationofbreak-pointlocationsintheCEalgorithmbasedonthefourparameterbetadistributionandtruncatednormaldistribution.ThegeneralBICorAICcanbeusedtoselecttheoptimalnumberofbreak-points.UsageCE.ZINB(data,Nmax=10,eps=0.01,rho=0.05,M=200,h=5,a=0.8,b=0.8,distyp=1,penalty="BIC",parallel=FALSE) 20CE.ZINB.Initobj1profilePlot(obj1,simdata)#Toobtainthemeanprofileplot##CEwithtruncatednormaldistributionwithBICastheselectioncriterion##obj2CE.ZINB(simdata,distyp=2,penalty=BIC,parallel=TRUE)#Parallelcomputationobj2profilePlot(obj2,simdata)#Toobtainthemeanprofileplot##End(Notrun) CE.ZINB.InitMultipleBreak-pointDetectionviatheCEMethodwithZero-InatedNegativeBinomialDistributionwithinitiallocations DescriptionPerformscalculationstoestimatethebreak-pointlocationswhentheirinitialvaluesaregiven.Zero-inatednegativebinomialdistributionisusedtomodeltheexcesszeroobservationsandtomodelover-dispersesionintheoberveddiscrete(count)data.Thisfunctionsupportsforthesimulationofbreak-pointlocationsintheCEalgorithmbasedonthefourparameterbetadistributionandtruncatednormaldistribution.ThegeneralBICorAICcanbeusedtoselecttheoptimalnumberofbreak-points.UsageCE.ZINB.Init(data,init.locs,eps=0.01,rho=0.05,M=200,h=5,a=0.8,b=0.8,distyp=1,penalty="BIC",var.init=1e+05,parallel=FALSE)Argumentsdatadatatobeanalysed.Asinglecolumnarrayoradataframe.init.locsInitialbreak-pointlocations.epsthecut-offvalueforthestoppingcriterionintheCEmethod.Defaultvalueis0.01.rhothefractionwhichisusedtoobtainthebestperformingsetofsamplesolutions(i.e.,elitesample).Defaultvalueis0.05.Msamplesizetobeusedinsimulatingthelocationsofbreak-points.Defaultvalueis200.hminimumaberrationwidth.Defaultis5.aasmoothingparametervalue.Itisusedinthefourparameterbetadistributiontosmoothbothshapeparameters.Whensimulatingfromthetruncatednormaldis-tribution,thisvalueisusedtosmooththeestimatesofthemeanvalues.Defaultis0.8. 22CE.ZINB.InitSchwarz,G.(1978)Estimatingthedimensionofamodel,TheAnnalsofStatistics,6(2),461-464.SeeAlsoCE.NBforCEwithnegativebinomial,CE.NB.InitforCEwithnegativebinomialwithinitiallocations,CE.ZINBforCEwithzero-inatednegativebinomial,profilePlottoobtainmeanproleplot.Examples####Simulateddataexample####gamlssRpackageisusedtosimulatedatafromtheZINB.##Notrun:library(gamlss)segs6#NumberofsegementsMc(1500,2200,800,2500,1000,2000)#Segmentwidth#true.locationsc(1501,3701,4501,7001,8001)#Truebreak-pointlocationssegNULLpc(0.6,0.1,0.3,0.05,0.2,0.4)#Specificationofp'soneachsegment'sigma.valc(1,2,3,4,5,6)#Specificationofsigmavlauesfor(jin1:segs){segc(seg,rZINBI(M[j],mu=300,sigma=sigma.val[j],nu=p[j]))}simdataas.data.frame(seg)rm(p,M,seg,segs,j,sigma.val)#plot(data[,1])##CEwiththefourparameterbetadistributionwithBICastheselectioncriterion##init.locic(1400,3400,4650,7100,8200)obj1CE.ZINB.Init(simdata,init.locs=init.loci,distyp=1,penalty=BIC,parallel=TRUE)obj1profilePlot(obj1,simdata)#Toobtainthemeanprofileplot##CEwithtruncatednormaldistributionwithBICastheselectioncriterion##obj2CE.ZINB.Init(simdata,init.locs=init.loci,distyp=2,penalty=BIC,parallel=TRUE)obj2profilePlot(obj2,simdata)#Toobtainthemeanprofileplot##End(Notrun) 24prolePlot profilePlotMeanproleplot DescriptionPlottingfunctiontoobtainmeanproleplotofthetestingdatasetbasedontheestimatesofthebreak-points.AnRobjectcreatedfromtheCE.Normal,CE.NBotCE.ZINBisrequired.Usercanaltertheaxisnames.UsageprofilePlot(obj,data,x.label="DataSequence",y.label="Value")ArgumentsobjRobjectcreatedfromCE.Normal,CE.NBorCE.ZINB.datadatatobeanalysed.Asinglecolumnarrayoradataframe.x.labelxaxislabel.Defaultis"DataSequence".y.labelyaxislabel.Defaultis"Value".Author(s)Priyadarshana,W.J.R.M.w&#xmjay;ꅐardana@swin.edu.auSeeAlsoCE.Normal.Mean,CE.NB,CE.ZINB.Examplesdata(ch1.GM03563)##Notrun:##CEwithfourparameterbetadistribution##obj1CE.Normal.Mean(ch1.GM03563,distyp=1,penalty="mBIC",parallel=TRUE)profilePlot(obj1)##CEwithtruncatednormaldistribution##obj2CE.Normal.Mean(ch1.GM03563,distyp=2,penalty="mBIC",parallel=TRUE)profilePlot(obj2)##End(Notrun)