{"id":3348,"date":"2023-07-17T23:22:52","date_gmt":"2023-07-17T23:22:52","guid":{"rendered":"https:\/\/statorials.org\/tr\/uc-yollu-anova-pitonu\/"},"modified":"2023-07-17T23:22:52","modified_gmt":"2023-07-17T23:22:52","slug":"uc-yollu-anova-pitonu","status":"publish","type":"post","link":"https:\/\/statorials.org\/tr\/uc-yollu-anova-pitonu\/","title":{"rendered":"Python'da \u00fc\u00e7 yollu anova nas\u0131l ger\u00e7ekle\u015ftirilir"},"content":{"rendered":"

<\/p>\n

\n

\u00dc\u00e7 fakt\u00f6re da\u011f\u0131lm\u0131\u015f \u00fc\u00e7 veya daha fazla ba\u011f\u0131ms\u0131z grubun ortalamalar\u0131 aras\u0131nda istatistiksel olarak anlaml\u0131 bir fark olup olmad\u0131\u011f\u0131n\u0131 belirlemek i\u00e7in \u00fc\u00e7 y\u00f6nl\u00fc ANOVA<\/strong> kullan\u0131l\u0131r.<\/span><\/p>\n

A\u015fa\u011f\u0131daki \u00f6rnek Python’da \u00fc\u00e7 y\u00f6nl\u00fc ANOVA’n\u0131n nas\u0131l ger\u00e7ekle\u015ftirilece\u011fini g\u00f6sterir.<\/span><\/p>\n

\u00d6rnek: Python’da \u00dc\u00e7 Yollu ANOVA<\/strong><\/span><\/h2>\n

Bir ara\u015ft\u0131rmac\u0131n\u0131n, iki antrenman program\u0131n\u0131n kolej basketbolcular\u0131 aras\u0131nda s\u0131\u00e7rama y\u00fcksekli\u011finde farkl\u0131 ortalama iyile\u015fmelere yol a\u00e7\u0131p a\u00e7mad\u0131\u011f\u0131n\u0131 belirlemek istedi\u011fini varsayal\u0131m.<\/span><\/p>\n

Ara\u015ft\u0131rmac\u0131, cinsiyet ve b\u00f6l\u00fcnmenin (B\u00f6l\u00fcm I veya II) de atlama y\u00fcksekli\u011fini etkileyebilece\u011finden \u015f\u00fcpheleniyor, bu nedenle bu fakt\u00f6rler hakk\u0131nda da veri topluyor.<\/span><\/p>\n

Amac\u0131, antrenman program\u0131n\u0131n, cinsiyetin ve b\u00f6l\u00fcm\u00fcn atlama y\u00fcksekli\u011fini nas\u0131l etkiledi\u011fini belirlemek i\u00e7in \u00fc\u00e7 y\u00f6nl\u00fc bir ANOVA ger\u00e7ekle\u015ftirmektir.<\/span><\/p>\n

Python’da bu \u00fc\u00e7 y\u00f6nl\u00fc ANOVA’y\u0131 ger\u00e7ekle\u015ftirmek i\u00e7in a\u015fa\u011f\u0131daki ad\u0131mlar\u0131 kullan\u0131n:<\/span><\/p>\n

1. Ad\u0131m: Verileri olu\u015fturun<\/strong><\/span><\/p>\n

\u00d6ncelikle verileri tutacak bir pandas DataFrame olu\u015ftural\u0131m:<\/span><\/p>\n

 import<\/span> numpy as<\/span> np\nimport<\/span> pandas as<\/span> pd\n\n#createDataFrame\n<\/span>df = pd. DataFrame<\/span> ({' program<\/span> ': np.repeat<\/span> ([1,2],20),\n                   ' gender<\/span> ': np. tile<\/span> (np. repeat<\/span> (['M', 'F'], 10), 2),\n                   ' division<\/span> ': np. tile<\/span> (np. repeat<\/span> ([1, 2], 5), 4),\n                   ' height<\/span> ': [7, 7, 8, 8, 7, 6, 6, 5, 6, 5,\n                              5, 5, 4, 5, 4, 3, 3, 4, 3, 3,\n                              6, 6, 5, 4, 5, 4, 5, 4, 4, 3,\n                              2, 2, 1, 4, 4, 2, 1, 1, 2, 1]})\n\n#view first ten rows of DataFrame \n<\/span>df[:10]\n\n\tprogram gender division height\n0 1 M 1 7\n1 1 M 1 7\n2 1 M 1 8\n3 1 M 1 8\n4 1 M 1 7\n5 1 M 2 6\n6 1 M 2 6\n7 1 M 2 5\n8 1 M 2 6\n9 1 M 2 5\n<\/strong><\/span><\/pre>\n
 Ad\u0131m 2: \u00dc\u00e7 y\u00f6nl\u00fc ANOVA’y\u0131 ger\u00e7ekle\u015ftirin<\/strong><\/span><\/p>\n
 Daha sonra, \u00fc\u00e7 y\u00f6nl\u00fc ANOVA’y\u0131 ger\u00e7ekle\u015ftirmek i\u00e7in statsmodels<\/strong> k\u00fct\u00fcphanesindeki anova_lm()<\/strong> fonksiyonunu kullanabiliriz:<\/span><\/p>\n
 import<\/span> statsmodels. api<\/span> as<\/span> sm\nfrom<\/span> statsmodels. formula<\/span> . api<\/span> import<\/span> ols\n\n#perform three-way ANOVA\n<\/span>model = ols(\"\"\"height ~ C(program) + C(gender) + C(division) +\n               C(program):C(gender) + C(program):C(division) + C(gender):C(division) +\n               C(program):C(gender):C(division)\"\"\", data=df) .fit<\/span> ()\n\nsm. stats<\/span> . anova_lm<\/span> (model, typ= 2<\/span> )\n\n\t                          sum_sq df F PR(>F)\nC(program) 3.610000e+01 1.0 6.563636e+01 2.983934e-09\nC(gender) 6.760000e+01 1.0 1.229091e+02 1.714432e-12\nC(division) 1.960000e+01 1.0 3.563636e+01 1.185218e-06\nC(program):C(gender) 2.621672e-30 1.0 4.766677e-30 1.000000e+00\nC(program):C(division) 4.000000e-01 1.0 7.272727e-01 4.001069e-01\nC(gender):C(division) 1.000000e-01 1.0 1.818182e-01 6.726702e-01\nC(program):C(gender):C(division) 1.000000e-01 1.0 1.818182e-01 6.726702e-01\nResidual 1.760000e+01 32.0 NaN NaN<\/strong><\/span><\/pre>\n
 3. Ad\u0131m: Sonu\u00e7lar\u0131 yorumlay\u0131n<\/strong><\/span><\/p>\n
 Pr(>F)<\/strong> s\u00fctunu, her bir fakt\u00f6r i\u00e7in p-de\u011ferini ve fakt\u00f6rler aras\u0131ndaki etkile\u015fimleri g\u00f6r\u00fcnt\u00fcler.<\/span><\/p>\n
 Sonu\u00e7lardan, \u00fc\u00e7 fakt\u00f6r aras\u0131ndaki etkile\u015fimlerin hi\u00e7birinin istatistiksel olarak anlaml\u0131 olmad\u0131\u011f\u0131n\u0131 g\u00f6rebiliriz.<\/span><\/p>\n
 Ayr\u0131ca \u00fc\u00e7 fakt\u00f6r\u00fcn (program, cinsiyet ve b\u00f6l\u00fcm) her birinin a\u015fa\u011f\u0131daki p de\u011ferleri ile istatistiksel olarak anlaml\u0131 oldu\u011funu da g\u00f6rebiliriz:<\/span><\/p>\n