统计软件SAS教程SAS练习.docx

1、统计软件SAS教程SAS练习统计软件SAS教程SAS练习libname dy d:dzwj; data dy.by_student; proc print data=dy.c9501; by sex; /*分类*/ run; proc print; run; (女性一栏无法输出，并且满足条件的男性没有输出来) libname dy d:dzwj; data dy.sum_bkmoney; proc print data=dy.bkmoney noobs; sum amount;/*sum函数求和*/ run; libname dy d:dzwj; proc sort data=dy.c9501

2、; by name; proc sort data=dy.bkmoney; by name; data dy.c9501bk; merge dy.c9501 dy.bkmoney;/*merge横向合并*/ by name; run; proc sort data=dy.c9501bk; by sex; proc print data=dy.c9501bk; by sex; sum amount; run; libname dy d:dzwj; data dy.table_c9501bk; proc tabulate data=dy.c9501bk; /* tabulate 分类汇总 */ c

3、lass sex; var amount; table sex,amount; run; proc print; run; (出现乱码) libname dy d:dzwj; data dy.meanstd_c9501; proc tabulate data=dy.c9501bk; class sex; var math chinese; table sex,(math chinese)*(mean std); /*求变量的均值*/ run; proc print; run; libname dy d:dzwj; data dy.meanstd_c9501; proc tabulate dat

4、a=dy.c9501bk; class sex; var math chinese; table all sex,(math chinese)*(mean std); /*求所有的变量的均值*/ run; proc print; run; libname dy d:dzwj; data dy.meanstd_c9501; proc tabulate data=dy.c9501bk; class sex; var math chinese; table (sex all)*(N PCTN); /*频数分布*/ run; proc print; run; libname dy d:dzwj; da

5、ta dy.meanstd_c9501; proc tabulate data=dy.c9501bk; class sex; var math chinese; table (sex all)*math*(mean std); /*指定变量math的均值和方差*/ run; proc print; run; libname dy d:dzwj; data dy.meanstd_c9501; proc tabulate data=dy.c9501bk; class sex; var math chinese; table (sex all),(math chinese)*(mean std);

6、/*统计量加标签*/ keylabel mean=平均值 std=标准差 all=总计; label sex=性别 math=数学 chinese=语文; run; proc print; run; libname dy d:dzwj; data dy.meanstd_c9501; proc tabulate data=dy.c9501bk; class sex; var math chinese; table (sex all=总计),(math chinese)*(mean=平均值 std=标准差); /*统计量加标签，标签加在其中*/ label sex=性别 math=数学 chine

7、se=语文; run; proc print; run; (结果如上图所示) libname dy d:dzwj; data dy.by_sex; proc sort data=dy.c9501; by sex; run; proc print; run; libname dy d:dzwj; data dy.by_sex; proc sort data=dy.c9501; by sex descending math; run; proc print; run; (矩阵的转置没有实现，165页) libname dy d:dzwj; data dy.means_c9501; proc mea

8、ns data=dy.c9501; /*描述性统计*/ run; proc print; run; libname dy d:dzwj; data dy.freq_c9501; proc freq data=dy.c9501; /*求频率和累计值*/ tables sex; run; proc print; run; 第五章 多元统计分析 主分量分析: LIBNAME dy d:dzwj; DATA dy.TEMPERAT; INPUT CITY $ JANUARY JULY; CARDS; MOBILE 10.7 27.6 PHOENIX 10.7 32.9 LITTLE ROCK 4.2

9、27.4 SACRAMENTO 7.3 24.0 DENVER -1.2 22.8 HARTFORD -4.0 22.6 WILMINGTON 0.0 24.3 WASHINGTON DC 2.0 25.9 JACKSONVILLE 12.6 27.2 MOBILE 10.7 27.6 PHOENIX 10.7 32.9 LITTLE ROCK 4.2 27.4 SACRAMENTO 7.3 24.0 DENVER -1.2 22.8 HARTFORD -4.0 22.6 WILMINGTON 0.0 24.3 WASHINGTON DC 2.0 25.9 JACKSONVILLE 12.6

10、27.2 SIOUX FALLS -9.9 22.9 MEMPHIS 4.7 26.4 NASHVILLE 3.5 26.4 DALLAS 7.1 29.3 EL PASO 6.4 27.9 HOUSTON 11.2 28.5 SALT LAKE CITY -2.2 24.8 BURLINGTON -8.4 21.0 NORFOLK 4.7 25.7 RICHMOND 3.1 25.5 SPOKANE -3.7 20.9 CHARLESTON, WV 1.4 23.9 MILWAUKEE -7.0 21.1 CHEYENNE -3.0 20.6 ; PROC PRINCOMP COV OUT=

11、PRIN; /*主分量也就是主成分的意思，out保护原始数据和主分量得分的数据集从协方差阵出发计算主分量*/ VAR JULY JANUARY; RUN; libname dy d:dzwj; data dy.crime; title 各州每十万人的犯罪率; INPUT STATE$ MURDER RAPE ROBBERY ASSAULT BURGLARY LARCENY AUTO; CARDS; ALABAMA 14.2 25.2 96.8 278.3 1135.5 1881.9 280.7 ALASKA 10.8 51.6 96.8 284.0 1331.7 3369.8 753.3 AR

12、IZONA 9.5 34.2 138.2 312.3 2346.1 4467.4 439.5 ARKANSAS 8.8 27.6 83.2 203.4 972.6 1862.1 183.4 CALIFORNIA 11.5 49.4 287.0 358.0 2139.4 3499.8 663.5 COLORADO 6.3 42.0 170.7 292.9 1935.2 3903.2 477.1 CONNECTICUT 4.2 16.8 129.5 131.8 1346.0 2620.7 593.2 DELAWARE 6.0 24.9 157.0 194.2 1682.6 3678.4 467.0

13、 FLORIDA 10.2 39.6 187.9 449.1 1859.9 3840.5 351.4 GEORGIA 11.7 31.1 140.5 256.5 1351.1 2170.2 297.9 HAWAII 7.2 25.5 128.0 64.1 1911.5 3920.4 489.4 IDAHO 5.5 19.4 39.6 172.5 1050.8 2599.6 237.6 ILLINOIS 9.9 21.8 211.3 209.0 1085.0 2828.5 528.6 INDIANA 7.4 26.5 123.2 153.5 1086.2 2498.7 377.4 IOWA 2.

14、3 10.6 41.2 89.8 812.5 2685.1 219.9 KANSAS 6.6 22.0 100.7 180.5 1270.4 2739.3 244.3 KENTUCKY 10.1 19.1 81.1 123.3 872.2 1662.1 245.4 LOUISIANA 15.5 30.9 142.9 335.5 1165.5 2469.9 337.7 MAINE 2.4 13.5 38.7 170.0 1253.1 2350.7 246.9 MARYLAND 8.0 34.8 292.1 358.9 1400.0 3177.7 428.5 MASSACHUSETTS 3.1 2

15、0.8 169.1 231.6 1532.2 2311.3 1140.1 MICHIGAN 9.3 38.9 261.9 274.6 1522.7 3159.0 545.5 MINNESOTA 2.7 19.5 85.9 85.8 1134.7 2559.3 343.1 MISSISSIPPI 14.3 19.6 65.7 189.1 915.6 1239.9 144.4 MISSOURI 9.6 28.3 189.0 233.5 1318.3 2424.2 378.4 MONTANA 5.4 16.7 39.2 156.8 804.9 2773.2 309.2 NEBRASKA 3.9 18

16、.1 64.7 112.7 760.0 2316.1 249.1 NEVADA 15.8 49.1 323.1 355.0 2453.1 4212.6 559.2 NEW HAMPSHIRE 3.2 10.7 23.2 76.0 1041.7 2343.9 293.4 NEW JERSEY 5.6 21.0 180.4 185.1 1435.8 2774.5 511.5 NEWMEXICO 8.8 39.1 109.6 343.4 1418.7 3008.6 259.5 NEWYORK 10.7 29.4 472.6 319.1 1728.0 2782.0 745.8 NORTH CAROLI

17、NA 10.6 17.0 61.3 318.3 1154.1 2037.8 192.1 NORTH DAKOTA 0.9 9.0 13.3 43.8 446.1 1843.0 144.7 OHIO 7.8 27.3 190.5 181.1 1216.0 2696.8 400.4 OKLAHOMA 8.6 29.2 73.8 205.0 1288.2 2228.1 326.8 OREGON 4.9 39.9 124.1 286.9 1636.4 3506.1 388.9 PENNSYLVANIA 5.6 19.0 130.3 128.0 877.5 1624.1 333.2 RHODE ISLA

18、ND 3.6 10.5 86.5 201.0 1489.5 2844.1 791.4 SOUTH CAROLINA 11.9 33.0 105.9 485.3 1613.6 2342.4 245.1 SOUTH DAKOTA 2.0 13.5 17.9 155.7 570.5 1704.4 147.5 TENNESSEE 10.1 29.7 145.8 203.9 1259.7 1776.5 314.0 TEXAS 13.3 33.8 152.4 208.2 1603.1 2988.7 397.6 UTAH 3.5 20.3 68.8 147.3 1171.6 3004.6 334.5 VER

19、MONT 1.4 15.9 30.8 101.2 1348.2 2201.0 265.2 VIRGINIA 9.0 23.3 92.1 165.7 986.2 2521.2 226.7 WASHINGTON 4.3 39.6 106.2 224.8 1605.6 3386.9 360.3 WESTVIRGINIA 6.0 13.2 42.2 90.9 597.4 1341.7 163.3 WISCONSIN 2.8 12.9 52.2 63.7 846.9 2614.2 220.7 WYOMING 5.4 21.9 39.7 173.9 811.6 2772.2 282.0 ; PROC PR

20、INCOMP COV OUT=CRIMCOMP; RUN; PROC SORT; BY PRIN1; PROC PRINT; ID STATE; VAR PRIN1 PRIN2 MURDER RAPE ROBBERY ASSAULT BURGLARY LARCENY AUTO; TITLE2 各州按第一主分量作为金钱犯罪与暴力对比的排列 ; PROC SORT; BY PRIN2; PROC PRINT; ID STATE; VAR PRIN1 PRIN2 MURDER RAPE ROBBERY ASSAULT BURGLARY LARCENY AUTO; TITLE2 各州按第二主分量作为金

21、钱犯罪与暴力对比的排列 ; GOPTIONS FTEXT=宋体; PROC GPLOT; PLOT PRIN2*PRIN1=STATE; TITLE2 前两个主分量的散点图; PROC GPLOT; PLOT PRIN3*PRIN1=STATE; TITLE2 第一、三主分量的散点图; RUN; 因子分析: libname dy d:dzwj; DATA dy.SOCECON; TITLE 五个经济指标的分析; INPUT POP SCHOOL EMPLOY SERVICES HOUSE; CARDS; 5700 12.8 2500 270 25000 1000 10.9 600 10 100

22、00 3400 8.8 1000 10 9000 3800 13.6 1700 140 25000 4000 12.8 1600 140 25000 8200 8.3 2600 60 12000 1200 11.4 400 10 16000 9100 11.5 3300 60 14000 9900 12.5 3400 180 18000 9600 13.7 3600 390 25000 9600 9.6 3300 80 12000 9400 11.4 4000 100 13000 ; PROC FACTOR DATA=dy.SOCECON SIMPLE CORR; /*因子分析，就进行简单的相关性*/ TITLE2 主分量分析; RUN; 判别分析: 和聚类分析比较难懂 第四章 基本统计分析