Session16多元数据分析.ppt

《Session16多元数据分析.ppt》由会员上传分享，免费在线阅读，更多相关内容在行业资料-天天文库。

1、Data,ModelandDecisions数据、模型与决策Session16MultivariateDataAnalysis多元数据分析ClusterAnalysis聚类分析SessionTopicsOverview概览BasicConcept基本概念StatisticsClusterAnalysis统计聚类分析ConductingClusterAnalysis实施聚类分析NonhierarchicalClustering非层次聚类ClusteringVariables聚类变量FocusonNAPCNA

2、PC公司应用Summary总结ClusterAnalysis聚类分析ClusterAnalysisDefinedClusteranalysisisaprocedureforidentifyingsubgroupsofindividualsoritemsthatarehomogeneouswithinsubgroupsanddifferentfromothersubgroups.聚类分析是对个体或事物进行分类，以使得每个类别中的个体或事物在某种意义下是相似的，而类别之间是有很大的差别的一种统计方法。AnId

3、ealClusteringSituation理想的聚类情况Variable2Variable1APracticalClusteringSituation实际聚类情况Variable1XVariable2ConductingClusterAnalysis实施聚类分析SelectaDistanceMeasureFormulatetheProblemSelectaClusteringProcedureDecideontheNumberofClustersInterpretandProfileClustersAs

4、sesstheValidityofClustering描述问题选择距离度量选择聚类方法决定聚类数目解释和描述聚类检验评价聚类CaseNo.V1V2V3V4V5V61647323223145437264134464536513226466463347536334873741492433631035364611132353125454241322154414464647156542141635464717447225183726431946372720232472ClusteringData聚类数据Clust

5、eringProcedures聚类方法ClusteringProceduresHierarchicalNonhierarchicalAgglomerativeDivisiveSequentialThresholdParallelThresholdOptimizingPartitioningLinkageMethodsVarianceMethodsCentroidMethodsWard’sMethodSingleCompleteAverage聚类方法层次聚类非层次聚类聚合聚类分离聚类序列门槛平行门槛最优分割

6、关联法方差法质心法沃尔德法单个完全平均LinkageMethodsofClustering聚类连接方法SingleLinkageMinimumDistanceCompleteLinkageMaximumDistanceAverageLinkageAverageDistanceCluster1Cluster2Cluster1Cluster2Cluster1Cluster2OtherAgglomerativeClusteringMethods其它聚合聚类方法Ward’sProcedureCentroidMet

7、hodVerticalIciclePlotUsingWard’sMethod冰状图111211111118+1+4+5+6+7+2+3+11+12+13+14+9+10+16+19+17+18+15+98404096328315762751CaseLabelandNumberNumberofClustersResultsofHierarchicalClusteringStageclusterClusterscombinedfirstappearsStageCluster1Cluster2Coeffic

8、ientCluster1Cluster2Nextstage114161.00000000722132.500000001537124.000000001045115.50000000115387.00000000166168.50000000107101410.166667019892012.6666670011941015.2500000712101718.2500006313115922.75000048151241927