R’de sa\u011flam regresyon ger\u00e7ekle\u015ftirmek i\u00e7in, a\u015fa\u011f\u0131daki s\u00f6zdizimini kullanan MASS<\/strong> paketindeki rlm()<\/strong> i\u015flevini kullanabiliriz:<\/span><\/p>\n A\u015fa\u011f\u0131daki ad\u0131m ad\u0131m \u00f6rnek, belirli bir veri k\u00fcmesi i\u00e7in R’de sa\u011flam regresyonun nas\u0131l ger\u00e7ekle\u015ftirilece\u011fini g\u00f6sterir.<\/span><\/p>\n \u00d6ncelikle \u00e7al\u0131\u015fmak i\u00e7in sahte bir veri k\u00fcmesi olu\u015ftural\u0131m:<\/span><\/p>\n Daha sonra, s\u0131radan bir en k\u00fc\u00e7\u00fck kareler regresyon modelini yerle\u015ftirelim ve standartla\u015ft\u0131r\u0131lm\u0131\u015f art\u0131klar\u0131n<\/a> bir grafi\u011fini olu\u015ftural\u0131m.<\/span><\/p>\n Pratikte, mutlak de\u011feri 3’ten b\u00fcy\u00fck olan herhangi bir standartla\u015ft\u0131r\u0131lm\u0131\u015f art\u0131k de\u011feri genellikle ayk\u0131r\u0131 de\u011fer olarak kabul ederiz.<\/span> <\/p>\n Grafikten, standartla\u015ft\u0131r\u0131lm\u0131\u015f art\u0131klar\u0131n 3 civar\u0131nda oldu\u011fu iki g\u00f6zlemin oldu\u011funu g\u00f6rebiliriz.<\/span><\/p>\n Bu, veri k\u00fcmesinde iki potansiyel ayk\u0131r\u0131 de\u011fer oldu\u011funu ve dolay\u0131s\u0131yla bunun yerine sa\u011flam regresyondan yararlanabilece\u011fimizi g\u00f6sterir.<\/span><\/p>\n Daha sonra sa\u011flam bir regresyon modeline uyum sa\u011flamak i\u00e7in rlm()<\/strong> fonksiyonunu kullanal\u0131m:<\/span><\/p>\n Bu sa\u011flam regresyon modelinin OLS modeline k\u0131yasla verilere daha iyi uyum sa\u011flay\u0131p sa\u011flamad\u0131\u011f\u0131n\u0131 belirlemek i\u00e7in her modelin art\u0131k standart hatas\u0131n\u0131 hesaplayabiliriz.<\/span><\/p>\n Art\u0131k standart hata (RSE), bir regresyon modelinde art\u0131klar\u0131n standart sapmas\u0131n\u0131 \u00f6l\u00e7menin bir yoludur. CSR de\u011feri ne kadar d\u00fc\u015f\u00fck olursa, model verilere o kadar iyi uyum sa\u011flayabilir.<\/span><\/p>\n A\u015fa\u011f\u0131daki kod, her model i\u00e7in RSE’nin nas\u0131l hesaplanaca\u011f\u0131n\u0131 g\u00f6sterir:<\/span><\/p>\n Sa\u011flam regresyon modelinin RSE’sinin s\u0131radan en k\u00fc\u00e7\u00fck kareler regresyon modelinden \u00e7ok daha d\u00fc\u015f\u00fck oldu\u011funu g\u00f6rebiliyoruz, bu da bize sa\u011flam regresyon modelinin verilere daha iyi uyum sa\u011flad\u0131\u011f\u0131n\u0131 s\u00f6yl\u00fcyor.<\/span><\/p>\n R’de basit do\u011frusal regresyon nas\u0131l ger\u00e7ekle\u015ftirilir<\/a> Robust regresyon , \u00fczerinde \u00e7al\u0131\u015ft\u0131\u011f\u0131m\u0131z veri setinde ayk\u0131r\u0131 de\u011ferlerin veya etkili g\u00f6zlemlerin oldu\u011fu durumlarda s\u0131radan en k\u00fc\u00e7\u00fck kareler regresyonuna alternatif olarak kullanabilece\u011fimiz bir y\u00f6ntemdir. R’de sa\u011flam regresyon ger\u00e7ekle\u015ftirmek i\u00e7in, a\u015fa\u011f\u0131daki s\u00f6zdizimini kullanan MASS paketindeki rlm() i\u015flevini kullanabiliriz: A\u015fa\u011f\u0131daki ad\u0131m ad\u0131m \u00f6rnek, belirli bir veri k\u00fcmesi i\u00e7in R’de sa\u011flam regresyonun nas\u0131l ger\u00e7ekle\u015ftirilece\u011fini g\u00f6sterir. 1. Ad\u0131m: Verileri […]<\/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-1608","post","type-post","status-publish","format-standard","hentry","category-rehber"],"yoast_head":"\n 1. Ad\u0131m: Verileri olu\u015fturun<\/strong><\/span><\/h3>\n
#create data<\/span>\ndf <- data. frame<\/span> (x1=c(1, 3, 3, 4, 4, 6, 6, 8, 9, 3,\n 11, 16, 16, 18, 19, 20, 23, 23, 24, 25),\n x2=c(7, 7, 4, 29, 13, 34, 17, 19, 20, 12,\n 25, 26, 26, 26, 27, 29, 30, 31, 31, 32),\n y=c(17, 170, 19, 194, 24, 2, 25, 29, 30, 32,\n 44, 60, 61, 63, 63, 64, 61, 67, 59, 70))\n\n#view first six rows of data\n<\/span>head(df)\n\n x1 x2 y\n1 1 7 17\n2 3 7 170\n3 3 4 19\n4 4 29 194\n5 4 13 24\n6 6 34 2\n<\/strong><\/pre>\n Ad\u0131m 2: S\u0131radan En K\u00fc\u00e7\u00fck Kareler Regresyonunu Ger\u00e7ekle\u015ftirin<\/strong><\/span><\/h3>\n
#fit ordinary least squares regression model<\/span>\nols <- lm(y~x1+x2, data=df)\n\n#create plot of y-values vs. standardized residuals\n<\/span>plot(df$y, rstandard(ols), ylab=' Standardized Residuals<\/span> ', xlab=' y<\/span> ') \nabline(h= 0<\/span> )<\/strong> <\/pre>\n![\"\"](\"https:\/\/statorials.org\/wp-content\/uploads\/2023\/08\/robusteregr1.png\")
<\/p>\n Ad\u0131m 3: Sa\u011flam Regresyon Ger\u00e7ekle\u015ftirin<\/strong><\/span><\/h3>\n
library<\/span> (MASS)<\/span>\n\n#fit robust regression model<\/span>\nrobust <- rlm(y~x1+x2, data=df)<\/strong><\/pre>\n #find residual standard error of ols model\n<\/span>summary(ols)$sigma\n\n[1] 49.41848\n\n#find residual standard error of ols model\n<\/span>summary(robust)$sigma\n\n[1] 9.369349\n<\/strong><\/pre>\n Ek kaynaklar<\/strong><\/span><\/h3>\n
R’de \u00e7oklu do\u011frusal regresyon nas\u0131l ger\u00e7ekle\u015ftirilir<\/a>
R’de polinom regresyonu nas\u0131l ger\u00e7ekle\u015ftirilir<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"