<\/p>\n
Regresyon analizinde, \u00e7oklu do\u011frusall\u0131k<\/a> , iki veya daha fazla yorday\u0131c\u0131 de\u011fi\u015fkenin regresyon modelinde benzersiz veya ba\u011f\u0131ms\u0131z bilgi sa\u011flamayacak \u015fekilde birbiriyle y\u00fcksek d\u00fczeyde korelasyona sahip olmas\u0131 durumunda ortaya \u00e7\u0131kar.<\/span><\/p>\n Yorday\u0131c\u0131 de\u011fi\u015fkenler aras\u0131ndaki korelasyon derecesi yeterince y\u00fcksekse, bu durum regresyon modelinin yerle\u015ftirilmesinde ve yorumlanmas\u0131nda sorunlara neden olabilir.<\/span><\/p>\n Bir regresyon modelinde \u00e7oklu do\u011frusall\u0131\u011f\u0131 tespit etmenin en basit yolu, varyans enflasyon fakt\u00f6r\u00fc olarak bilinen ve genellikle VIF<\/strong> olarak k\u0131salt\u0131lan bir \u00f6l\u00e7\u00fcm\u00fc hesaplamakt\u0131r.<\/span><\/p>\n VIF, bir modeldeki yorday\u0131c\u0131 de\u011fi\u015fkenler aras\u0131ndaki ili\u015fkinin g\u00fcc\u00fcn\u00fc \u00f6l\u00e7er. 1 ile pozitif sonsuz aras\u0131nda bir de\u011fer al\u0131r.<\/span><\/p>\n VIF de\u011ferlerini yorumlamak i\u00e7in a\u015fa\u011f\u0131daki temel kurallar\u0131 kullan\u0131r\u0131z:<\/span><\/p>\n A\u015fa\u011f\u0131daki \u00f6rnek, modeldeki her tahmin de\u011fi\u015fkeni i\u00e7in VIF de\u011ferlerini hesaplayarak Python’daki bir regresyon modelinde \u00e7oklu do\u011frusall\u0131\u011f\u0131n nas\u0131l tespit edilece\u011fini g\u00f6sterir.<\/span><\/p>\n \u00c7e\u015fitli basketbol oyuncular\u0131 hakk\u0131nda bilgi i\u00e7eren a\u015fa\u011f\u0131daki pandalar DataFrame’e sahip oldu\u011fumuzu varsayal\u0131m:<\/span><\/p>\n Yan\u0131t de\u011fi\u015fkeni olarak puanlamay\u0131<\/strong> ve tahmin de\u011fi\u015fkenleri olarak say\u0131<\/strong> , asist<\/strong> ve ribaundlar\u0131<\/strong> kullanarak \u00e7oklu do\u011frusal regresyon modelini<\/a> uydurmak istedi\u011fimizi varsayal\u0131m.<\/span><\/p>\n Modeldeki her tahmin de\u011fi\u015fkeninin VIF’sini<\/strong> hesaplamak i\u00e7in statsmodels<\/strong> k\u00fct\u00fcphanesindeki variance_inflation_factor()<\/a> fonksiyonunu kullanabiliriz:<\/span><\/p>\n Tahmin edici de\u011fi\u015fkenlerin her biri i\u00e7in VIF de\u011ferlerini g\u00f6rebiliriz:<\/span><\/p>\n Not:<\/strong> Bu de\u011fer alakal\u0131 olmad\u0131\u011f\u0131ndan \u015fablondaki “Kesi\u015fme” i\u00e7in VIF’yi g\u00f6z ard\u0131 edin.<\/span><\/p>\n Modeldeki yorday\u0131c\u0131 de\u011fi\u015fkenlerin VIF de\u011ferlerinin her biri 1’e yak\u0131n oldu\u011fundan \u00e7oklu do\u011frusall\u0131k modelde sorun te\u015fkil etmemektedir.<\/span><\/p>\n A\u015fa\u011f\u0131daki e\u011fitimlerde Python’da di\u011fer genel g\u00f6revlerin nas\u0131l ger\u00e7ekle\u015ftirilece\u011fi a\u00e7\u0131klanmaktad\u0131r:<\/span><\/p>\n Python’da basit do\u011frusal regresyon nas\u0131l ger\u00e7ekle\u015ftirilir<\/a> Regresyon analizinde, \u00e7oklu do\u011frusall\u0131k , iki veya daha fazla yorday\u0131c\u0131 de\u011fi\u015fkenin regresyon modelinde benzersiz veya ba\u011f\u0131ms\u0131z bilgi sa\u011flamayacak \u015fekilde birbiriyle y\u00fcksek d\u00fczeyde korelasyona sahip olmas\u0131 durumunda ortaya \u00e7\u0131kar. Yorday\u0131c\u0131 de\u011fi\u015fkenler aras\u0131ndaki korelasyon derecesi yeterince y\u00fcksekse, bu durum regresyon modelinin yerle\u015ftirilmesinde ve yorumlanmas\u0131nda sorunlara neden olabilir. Bir regresyon modelinde \u00e7oklu do\u011frusall\u0131\u011f\u0131 tespit etmenin en basit yolu, […]<\/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-3740","post","type-post","status-publish","format-standard","hentry","category-rehber"],"yoast_head":"\n\n
\u00d6rnek: Python’da \u00e7oklu ba\u011flant\u0131 testi<\/strong><\/span><\/h2>\n
import<\/span> pandas as<\/span> pd\n\n#createDataFrame<\/span>\ndf = pd. DataFrame<\/span> ({' rating<\/span> ': [90, 85, 82, 88, 94, 90, 76, 75, 87, 86],\n ' points<\/span> ': [25, 20, 14, 16, 27, 20, 12, 15, 14, 19],\n ' assists<\/span> ': [5, 7, 7, 8, 5, 7, 6, 9, 9, 5],\n ' rebounds<\/span> ': [11, 8, 10, 6, 6, 9, 6, 10, 10, 7]})\n\n#view DataFrame\n<\/span>print<\/span> (df)\n\n\trating points assists rebounds\n0 90 25 5 11\n1 85 20 7 8\n2 82 14 7 10\n3 88 16 8 6\n4 94 27 5 6\n5 90 20 7 9\n6 76 12 6 6\n7 75 15 9 10\n8 87 14 9 10\n9 86 19 5 7<\/strong><\/pre>\n from<\/span> patsy import<\/span> damatrices\nfrom<\/span> statsmodels. stats<\/span> . outliers_influence<\/span> import<\/span> variance_inflation_factor\n\n#find design matrix for regression model using 'rating' as response variable<\/span> \ny<\/span> ,<\/span>\n\n#create DataFrame to hold VIF values\n<\/span>vive_df = pd. DataFrame<\/span> ()\nvive_df[' variable<\/span> '] = X.columns<\/span> \n\n#calculate VIF for each predictor variable<\/span> \nvive_df[' VIF<\/span> '] = [variance_inflation_factor(X. values<\/span> , i) for<\/span> i in<\/span> range(X. shape<\/span> [1])]\n\n#view VIF for each predictor variable<\/span> \nprint<\/span> (viv_df)\n\n\t Variable VIF\n0 101.258171 Intercept\n1 1.763977 points\n2 1.959104 assists\n3 1.175030 rebounds<\/strong><\/pre>\n\n
Ek kaynaklar<\/strong><\/span><\/h2>\n
Python’da \u00e7oklu do\u011frusal regresyon nas\u0131l ger\u00e7ekle\u015ftirilir<\/a>
Python’da Art\u0131k Arsa Nas\u0131l Olu\u015fturulur<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"