SAS Markov Chain Monte Carlo (MCMC) Simulation in Practice

SAS Markov Chain Monte Carlo (MCMC) Simulation in Practice

ID:40725346

大小:2.12 MB

页数:20页

时间:2019-08-06

SAS Markov Chain Monte Carlo (MCMC) Simulation in Practice_第1页
SAS Markov Chain Monte Carlo (MCMC) Simulation in Practice_第2页
SAS Markov Chain Monte Carlo (MCMC) Simulation in Practice_第3页
SAS Markov Chain Monte Carlo (MCMC) Simulation in Practice_第4页
SAS Markov Chain Monte Carlo (MCMC) Simulation in Practice_第5页
资源描述:

《SAS Markov Chain Monte Carlo (MCMC) Simulation in Practice》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、PaperSP07®SASMarkovChainMonteCarlo(MCMC)SimulationinPracticeScottDPatterson,GlaxoSmithKline,KingofPrussia,PAShi-TaoYeh,GlaxoSmithKline,KingofPrussia,PAABSTRACTMarkovChainMonteCarlo(MCMC)isarandomsamplingmethodwithMonteCarlointegrationusingMarkovchains.MCMChasgainedpopularityinmanyapplicationsduetoth

2、eadvancementofcomputationalalgorithms®andpower.TheSASMIProcedureprovidesMCMCmethodforfillingarbitrarymissingdataandforsimulatingrandomsamplesbasedoncompletedatainformation.ExtensionsofthisprocedurearecurrentlyavailableinexperimentalformtoperformBayesianstatisticalanalysis.Thepurposeofthispaperistous

3、easimulatedhypotheticalclinicaltrialefficacydatasetandChallenger’sO-ringfailuredataasinputinordertoperformtheMCMCmethodformissingdataimputation,modelparametersimulation,andmodeldiagnostics,andtouseSAStoperformaBayesiananalysisofdatacommonlyencounteredinclinicaltrials.®®®®TheSASV9productsusedinthispa

4、perareSASBASE,SAS/STAT,andSAS/GRAPHonaPCWindowsplatform.INTRODUCTIONMonteCarlomethodsaresamplingtechniquesthatdrawpseudo-randomsamplesfromspecifiedprobabilitydistributions.Inotherwords,MonteCarlomethodsarenumericalmethodsthatutilizesequencenumbersofrandomnumberstoperformstatisticalsimulations.AMonte

5、Carloalgorithminvolvesthefollowingcomponents:1)probabilitydistributionfunctions(pdf’s)–thetargetdistributionmustbespecifiedbyasetofpdf’s,2)randomnumbergenerator–asourceofrandomnumbersuniformlydistributedontheunitinterval,3)samplingrule–aprescriptionforsamplingfromthespecifiedpdf’s,4)scoring–theoutco

6、mesmustbesummarizedintooverallscores,5)errorestimation–anestimateofthestatisticalerror(variance)asafunctionofthenumberoftrials,6)variancereductiontechniques–methodsforreducingthevarianceintheestimatedsolutiontoreducethecomputationaltime,7)parallelizationandvectorization–analgorithmtoallowMonteCarlom

7、ethodstobeimplementedefficientlyoncomputercomputation.Forindependentsamples,thesimulationoutcomescanapply‘LawofLargeNumbers’.ButindependentsamplingfromMonteCarlomethodsmaybedifficult.Theissueofindepen

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。