Ama\u00e7, her k\u00fcme i\u00e7indeki g\u00f6zlemlerin birbirine olduk\u00e7a benzer oldu\u011fu, farkl\u0131 k\u00fcmelerdeki g\u00f6zlemlerin ise birbirinden olduk\u00e7a farkl\u0131 oldu\u011fu k\u00fcmeleri bulmakt\u0131r.<\/span><\/p>\n SAS’ta k\u00fcmeleme yapman\u0131n en kolay yolu PROC CLUSTER<\/strong> kullanmakt\u0131r.<\/span><\/p>\n A\u015fa\u011f\u0131daki \u00f6rnek PROC CLUSTER’\u0131n<\/strong> pratikte nas\u0131l kullan\u0131laca\u011f\u0131n\u0131 g\u00f6stermektedir.<\/span><\/p>\n Diyelim ki 20 farkl\u0131 basketbolcunun say\u0131, asist ve ribaund bilgilerini i\u00e7eren a\u015fa\u011f\u0131daki veri setine sahibiz:<\/span> <\/p>\n Diyelim ki birbirine benzer istatistiklere sahip oyuncular\u0131n “k\u00fcmelerini” belirlemeye \u00e7al\u0131\u015fmak i\u00e7in baz\u0131 gruplamalar yapmak istiyoruz.<\/span><\/p>\n A\u015fa\u011f\u0131daki kod, k\u00fcmeleme ger\u00e7ekle\u015ftirmek i\u00e7in SAS’ta PROC CLUSTER’\u0131n<\/strong> nas\u0131l kullan\u0131laca\u011f\u0131n\u0131 g\u00f6sterir:<\/span><\/p>\n Sonucun ilk tablolar\u0131 k\u00fcmelemenin nas\u0131l yap\u0131ld\u0131\u011f\u0131na dair bilgi sa\u011flar:<\/span> <\/p>\n Veri k\u00fcmesindeki g\u00f6zlemler aras\u0131ndaki benzerli\u011fi g\u00f6rsel olarak inceleyebilmemiz i\u00e7in bir dendrogram da \u00fcretilir:<\/span> <\/p>\n Y ekseni bireysel g\u00f6zlemleri, x ekseni ise k\u00fcmeler aras\u0131ndaki ortalama mesafeyi g\u00f6sterir.<\/span><\/p>\n Bu dendrograma bak\u0131ld\u0131\u011f\u0131nda g\u00f6zlemlerin do\u011fal olarak \u00fc\u00e7 gruba ayr\u0131ld\u0131\u011f\u0131 g\u00f6r\u00fclmektedir:<\/span> <\/p>\n Daha sonra SAS’a orijinal veri k\u00fcmesindeki her g\u00f6zlemi \u00fc\u00e7 k\u00fcmeden birine atamas\u0131n\u0131 s\u00f6ylemek i\u00e7in ncl=3<\/strong> ile PROC TREE<\/strong> ifadesini kullanabiliriz:<\/span><\/p>\n Ortaya \u00e7\u0131kan veri seti, orijinal g\u00f6zlemlerin her birini ait olduklar\u0131 k\u00fcmeyle birlikte g\u00f6sterir:<\/span> <\/p>\n \u00d6rne\u011fin \u015funu g\u00f6rebiliriz:<\/span> 2, 3, 1, 4, 5, 7, 6 ve 19 kimlikli oyuncular\u0131n t\u00fcm\u00fc k\u00fcme 1’e<\/strong> aittir.<\/span><\/p>\n Bu bize bu sekiz oyuncunun say\u0131, asist ve ribaund de\u011fi\u015fkenleri a\u00e7\u0131s\u0131ndan \u201cbenzer\u201d oldu\u011funu g\u00f6steriyor.<\/span><\/p>\n Not<\/strong> : Bu \u00f6rnekte, k\u00fcmeleme i\u00e7in ba\u011flant\u0131 y\u00f6ntemi olarak ortalamay\u0131<\/strong> kullanmay\u0131 se\u00e7tik. Kullanabilece\u011finiz di\u011fer ba\u011flama y\u00f6ntemlerinin tam listesi i\u00e7in SAS belgelerine<\/a> bak\u0131n.<\/span><\/p>\n A\u015fa\u011f\u0131daki e\u011fitimlerde SAS’ta di\u011fer ortak g\u00f6revlerin nas\u0131l ger\u00e7ekle\u015ftirilece\u011fi a\u00e7\u0131klanmaktad\u0131r:<\/span><\/p>\n SAS’ta Temel Bile\u015fen Analizi Nas\u0131l Ger\u00e7ekle\u015ftirilir?<\/a> K\u00fcmeleme , bir veri seti i\u00e7indeki g\u00f6zlem gruplar\u0131n\u0131 bulmaya \u00e7al\u0131\u015fan bir makine \u00f6\u011frenme tekni\u011fidir. Ama\u00e7, her k\u00fcme i\u00e7indeki g\u00f6zlemlerin birbirine olduk\u00e7a benzer oldu\u011fu, farkl\u0131 k\u00fcmelerdeki g\u00f6zlemlerin ise birbirinden olduk\u00e7a farkl\u0131 oldu\u011fu k\u00fcmeleri bulmakt\u0131r. SAS’ta k\u00fcmeleme yapman\u0131n en kolay yolu PROC CLUSTER kullanmakt\u0131r. A\u015fa\u011f\u0131daki \u00f6rnek PROC CLUSTER’\u0131n pratikte nas\u0131l kullan\u0131laca\u011f\u0131n\u0131 g\u00f6stermektedir. \u00d6rnek: SAS’ta PROC CLUSTER nas\u0131l […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[11],"tags":[],"class_list":["post-4620","post","type-post","status-publish","format-standard","hentry","category-rehber"],"yoast_head":"\n \u00d6rnek: SAS’ta PROC CLUSTER nas\u0131l kullan\u0131l\u0131r?<\/strong><\/span><\/h2>\n
\/*create dataset*\/ \ndata<\/span><\/span> my_data;\n input<\/span> points assists rebounds; \n datalines<\/span> ;\n18 3 15\n20 3 14\n19 4 14\n14 5 10\n14 4 8\n15 7 14\n20 8 13\n28 7 9\n30 6 5\n31 9 4\n35 12 11\n33 14 6\n29 9 5\n25 9 5\n25 4 3\n27 3 8\n29 4 12\n30 12 7\n19 5 6\n23 11 5\n;\nrun<\/span> ;\n\n\/*view dataset*\/ \n<\/span>proc print<\/span> data<\/span> =my_data;\n<\/strong><\/span><\/pre>\n![\"\"](\"https:\/\/statorials.org\/wp-content\/uploads\/2023\/08\/clusters0.png\")
<\/p>\n \/*perform clustering using points, assists and rebounds variables*\/ \nproc cluster<\/span> data<\/span> =my_data method<\/span> =average;<\/span>\nvar<\/span> points assists rebounds;<\/span>\nrun<\/span> ;<\/span>\n<\/span><\/strong><\/span><\/pre>\n![\"\"](\"https:\/\/statorials.org\/wp-content\/uploads\/2023\/08\/clusters1.png\")
<\/p>\n![\"\"](\"https:\/\/statorials.org\/wp-content\/uploads\/2023\/08\/clusters2.png\")
<\/p>\n![\"SAS](\"https:\/\/statorials.org\/wp-content\/uploads\/2023\/08\/clusters3.png\")
<\/p>\n \/*assign each observation to one of three clusters*\/\n<\/span>proc tree<\/span> data<\/span> =clustd noprint ncl<\/span> =3 out<\/span> =clusts;\n copy<\/span> points assists rebounds;\n id<\/span> player_ID;\nrun<\/span> ;\nproc sort<\/span> ;\n by<\/span> cluster;\nrun<\/span> ;\n\n\/*view cluster assignments*\/\n<\/span>proc print<\/span> data<\/span> = clusters;\n id<\/span> player_ID;\nrun<\/span> ;<\/strong><\/span><\/pre>\n![\"\"](\"https:\/\/statorials.org\/wp-content\/uploads\/2023\/08\/clusters4.png\")
<\/p>\n Ek kaynaklar<\/strong><\/span><\/h2>\n
SAS’ta \u00e7oklu do\u011frusal regresyon nas\u0131l ger\u00e7ekle\u015ftirilir?<\/a>
SAS’ta lojistik regresyon nas\u0131l ger\u00e7ekle\u015ftirilir?<\/a><\/span><\/p>\n","protected":false},"excerpt":{"rendered":"