《聚类分析参考》由会员分享，可在线阅读，更多相关《聚类分析参考（9页珍藏版）》请在金锄头文库上搜索。
1、1.聚类分析PROCVARCLUS语句用来调用VARCLUS过程.其后的选项可以有输入输出的数据集选项，有关分类个数的选项，聚类方式选项（包括主成分法、重心法）等等，VAR语句列出被分析的变量.现有北京地区19511976年的气象资料，该资料见例9.1.要用重心法对变量Dec,Jan,Feb,High7,High4,High8进行聚类可采用以下SAS程序：datatepmeratinputyearDecJanFebhigh7high4high8;cards;19511.0-2.7-4.34-7121952-5.3-5.9-3.502151953-2.0-3.4-0.86-951954-5.7-
2、4.7-1.1101761955-0.9-3.8-3.115111956-5.7-5.3-5.9-31-121957-2.1-5.0-1.6-1531319580.6-4.3-0.210-301959-1.7-5.72.0-9-5-141960-3.6-3.6-1.311-3181961-3.6-3.1-0.85-1541962-0.1-3.9-1.181211963-2.6-3.0-5.2113-31964-1.4-4.9-1.7-11-871965-3.9-5.7-2.5-186-61966-4.7-4.8-3.3-9-6151967-6.0-5.6-4.040201968-1.7-6.4
3、-5.1-7-2-151969-3.4-5.6-2.0417-231970-3.1-4.2-2.99-16231971-3.8-4.9-3.9-135-21972-2.0-4.1-2.470101973-1.7-4.2-2.027-1141974-3.6-3.3-2.017-201975-2.7-3.70.1-1-13101976-2.4-7.6-2.259-30procvarclusdata=temperatcentroid;varDecJanFebhigh7high4high8;run;执行程序后，输出分成1类、2类、3类、4类的分法，仅考虑分为3类的表.OblipucCentroidCo
4、mponentClusterAnalysisClusterSummaryfor3cluster(s)ClusterClusterVariationProportionMembersvariationExplainedExplained133.000001.802810.6009221.000001.000001.0000312.000001.265200.6326Totalvariationexplained=4.068004Proportion=0.6780R-spuaredwithVARIABLEOwnClusterNextCloseat1-R*2RatioCluster1JAN0.817
5、20.20060.2287HIGH70.43830.02310.5749HIGH80.57690.14990.4977Cluster2HIGH41.00000.16530.0000Cluster3DEC0.63260.08010.3994FFB0.63260.04410.3844以上可见JAN,HIGH7,HIGH8为一组，HIGH4为一组，其余为一组2.判别分析已知长江中游6月份降水分三级：偏少、偏多、正常，分别用1,2,3来表示这三个母体.现利用19511975年共25年的观测资料（表15.6.1）建立四因子（指标）的三类判别函数.并将19761979年的观测资料（表15.6.2）作为检验
6、资料（主要是为了示范这类问题的SAS程序）.表15.6.1历年观测资料年份XX2X3X原分类19510.5882.044.040.6119520.4083.018.043.019530.5585.036.030.7219540.4085.036.040.7219550.4888.049.043.0219560.4182.035.078.6319570.6580.029.033.2119580.4582.032.033.131959：0.3981.027.046.5319600.3485.028.041.7319610.4284.038.020.4319620.5286.038.00.21196
7、30.4688.025.056.7219640.4883.046.013.6119650.5384.041.032.3119660.6581.031.028.9119670.6683.038.046.6119680.5380.042.093.1319690.5685.018.016.331970p.4583.027.023.9319710.3480.042.026.3319720.4179.038.040.8319730.5383.023.061.3319740.4884.019.023.2219750.3085.027.017.52表15.6.2检验数据（即作为待判样品）年份X1XXX4原分
8、类19760.4281.021.052.2319770.5281.038.045.8119780.3682.034.034.9219790.4384.034.060.5319761979的数据，作为待判数据，即假设不知其分类，而用19511975的数据，建立分类规则（判别函数）,从而将这4年分类，为此，我们可以取消这4年分类信息,和其余25年资料一同输入计算机,再用List选项列出重新分类结果;也可以将这4年资料存入一个检验数据集,通过testdata=选项说明这数据集是被分类的数据集,再用testlist列出它们的分类结果,前一方法也列出原来25个数据的回代分类,后一方法则不回代.本例设降水
9、量偏少为类型“1”，偏多类和正常为类型“2”，“3”，从而得出如下SAS程序：datarainfall；titleDiscriminantAnalisisofRianfalldata;inputyearx1-x4species;cards;19510.5882.044.040.6119520.4083.018.043.0219530.5585.036.030.7219540.4085.036.040.7219550.4888.049.043.0219560.4182.035.078.6319570.6580.029.033.2119580.4582.032.033.1319590.3981.0
10、27.046.5319600.3485.028.041.7319610.4284.038.020.4319620.5286.038.00.2119630.4688.025.056.7219640.4883.046.013.6119650.5384.041.032.3119660.6581.031.028.9119670.6683.038.046.6119680.5380.042.093.1319690.5685.018.016.3319700.4583.027.023.9319710.3480.042.026.3319720.4179.038.040.8319730.5383.023.061.
11、3319740.4884.019.023.2219750.3085.027.017.5219760.4281.021.052.2319770.5281.038.045.8119780.3682.034.034.9219790.3484.034.060.53procdiscrimdata=rainfalloutstat=infomethod=normallist;classspecies;varx1-x4;idyear;title2Usingnormalestmateswithusingcovarincematrix执行此程序后SAS给出许多表.DiscriminantAnalysisofRai
12、nfalldataUsingnormalestmateswithusingcovarineematrixDISCRIMINANTANALYSISLINEARDISCRIMINANTFUNCTION-1-1Constant=-.5XjcovxjCoefficientvector=covxj1SPECIES23CONSTANT-104.63242-76.74306-72.30675X1183.81847134.32274137.26505X20.947710.981720.88102X30.721440.445490.55155X4-0.12604-0.03259-0.04811上表为判为每-类的线性判别函数,例如样品X1=1,X2=2,X3=1.5,X4=1.7,判为第类的函数值为183.81847X1+0.94771X
