<\/p>\n
Goldfeld-Quandt testi,<\/strong> bir regresyon modelinde heteroskedastisitenin<\/a> mevcut olup olmad\u0131\u011f\u0131n\u0131 belirlemek i\u00e7in kullan\u0131l\u0131r.<\/span><\/p>\n De\u011fi\u015fen varyans, bir regresyon modelinde bir yan\u0131t de\u011fi\u015fkeninin<\/a> farkl\u0131 seviyelerindeki art\u0131klar\u0131n<\/a> e\u015fit olmayan da\u011f\u0131l\u0131m\u0131n\u0131 ifade eder.<\/span><\/p>\n E\u011fer heteroskedastisite mevcutsa, bu, do\u011frusal regresyonun, art\u0131klar\u0131n yan\u0131t de\u011fi\u015fkeninin her seviyesinde e\u015fit \u015fekilde da\u011f\u0131ld\u0131\u011f\u0131 y\u00f6n\u00fcndeki temel varsay\u0131mlar\u0131ndan<\/a> birini ihlal eder.<\/span><\/p>\n Bu e\u011fitimde Python’da Goldfeld-Quandt testinin nas\u0131l ger\u00e7ekle\u015ftirilece\u011fine ili\u015fkin ad\u0131m ad\u0131m bir \u00f6rnek sunulmaktad\u0131r.<\/span><\/p>\n Bu \u00f6rnek i\u00e7in bir s\u0131n\u0131ftaki 13 \u00f6\u011frencinin ders \u00e7al\u0131\u015fma saatleri, girilen haz\u0131rl\u0131k s\u0131navlar\u0131 ve final s\u0131nav sonu\u00e7lar\u0131na ili\u015fkin bilgileri i\u00e7eren a\u015fa\u011f\u0131daki pandas DataFrame’i olu\u015ftural\u0131m:<\/span><\/p>\n Daha sonra, yorday\u0131c\u0131 de\u011fi\u015fkenler olarak saatleri<\/strong> ve s\u0131navlar\u0131<\/strong> ve yan\u0131t de\u011fi\u015fkeni olarak puan\u0131<\/strong> kullanarak \u00e7oklu do\u011frusal regresyon modelini uygulayaca\u011f\u0131z:<\/span><\/p>\n Daha sonra Goldfeld-Quandt testini ger\u00e7ekle\u015ftirmek i\u00e7in statsmodels<\/strong> het_goldfeldquandt()<\/strong> fonksiyonunu kullanaca\u011f\u0131z.<\/span><\/p>\n Not<\/strong> : Goldfeld-Quandt testi, veri setinin merkezinde yer alan bir dizi g\u00f6zlemi kald\u0131rarak ve ard\u0131ndan art\u0131klar\u0131n da\u011f\u0131l\u0131m\u0131n\u0131n, merkezi g\u00f6zlemlerin her iki taraf\u0131n\u0131 ba\u011flayan sonu\u00e7ta ortaya \u00e7\u0131kan iki veri setinden farkl\u0131 olup olmad\u0131\u011f\u0131n\u0131 test ederek \u00e7al\u0131\u015f\u0131r.<\/span><\/p>\n Genellikle toplam g\u00f6zlemlerin yakla\u015f\u0131k %20’sini kald\u0131rmay\u0131 se\u00e7eriz. Bu durumda, g\u00f6zlemlerin %20’sini kald\u0131rmak istedi\u011fimizi belirtmek i\u00e7in drop<\/strong> arg\u00fcman\u0131n\u0131 kullanabiliriz:<\/span><\/p>\n Sonucun nas\u0131l yorumlanaca\u011f\u0131 a\u015fa\u011f\u0131da a\u00e7\u0131klanm\u0131\u015ft\u0131r:<\/span><\/p>\n Goldfeld-Quandt testi a\u015fa\u011f\u0131daki bo\u015f ve alternatif hipotezleri kullan\u0131r:<\/span><\/p>\n P de\u011feri 0,05’ten k\u00fc\u00e7\u00fck olmad\u0131\u011f\u0131ndan s\u0131f\u0131r hipotezini reddedemiyoruz.<\/span><\/p>\n Regresyon modelinde heteroskedastisitenin bir sorun oldu\u011funu iddia etmek i\u00e7in yeterli kan\u0131t\u0131m\u0131z yok.<\/span><\/p>\n Goldfeld-Quandt testinin bo\u015f hipotezini reddetmeyi ba\u015faramazsan\u0131z, o zaman de\u011fi\u015fen varyans mevcut de\u011fildir ve orijinal regresyonun sonucunu yorumlamaya devam edebilirsiniz.<\/span><\/p>\n Ancak s\u0131f\u0131r hipotezini reddederseniz bu, verilerde heteroskedastisitenin mevcut oldu\u011fu anlam\u0131na gelir. Bu durumda regresyon \u00e7\u0131kt\u0131 tablosunda g\u00f6r\u00fcnt\u00fclenen standart hatalar g\u00fcvenilir olmayabilir.<\/span><\/p>\n Bu sorunu \u00e7\u00f6zmenin birka\u00e7 yayg\u0131n yolu vard\u0131r:<\/span><\/p>\n 1. Yan\u0131t de\u011fi\u015fkenini d\u00f6n\u00fc\u015ft\u00fcr\u00fcn.<\/strong><\/span><\/p>\n Yan\u0131t de\u011fi\u015fkeni \u00fczerinde bir d\u00f6n\u00fc\u015f\u00fcm ger\u00e7ekle\u015ftirmeyi deneyebilirsiniz; \u00f6rne\u011fin yan\u0131t de\u011fi\u015fkeninin g\u00fcnl\u00fc\u011f\u00fcn\u00fc, karek\u00f6k\u00fcn\u00fc veya k\u00fcp k\u00f6k\u00fcn\u00fc<\/a> alabilirsiniz. Genellikle bu, heteroskedastisitenin ortadan kalkmas\u0131na neden olabilir.<\/span><\/p>\n 2. A\u011f\u0131rl\u0131kl\u0131 regresyon kullan\u0131n.<\/strong><\/span><\/p>\n A\u011f\u0131rl\u0131kl\u0131 regresyon, her veri noktas\u0131na, uydurulan de\u011ferin varyans\u0131na dayal\u0131 olarak bir a\u011f\u0131rl\u0131k atar. Temel olarak bu, daha y\u00fcksek varyansa sahip veri noktalar\u0131na d\u00fc\u015f\u00fck a\u011f\u0131rl\u0131k vererek bunlar\u0131n kalan karelerini azalt\u0131r.<\/span><\/p>\n Uygun a\u011f\u0131rl\u0131klar kullan\u0131ld\u0131\u011f\u0131nda a\u011f\u0131rl\u0131kl\u0131 regresyon, de\u011fi\u015fen varyans problemini ortadan kald\u0131rabilir.<\/span><\/p>\n A\u015fa\u011f\u0131daki e\u011fitimlerde Python’da di\u011fer yayg\u0131n i\u015flemlerin nas\u0131l ger\u00e7ekle\u015ftirilece\u011fi a\u00e7\u0131klanmaktad\u0131r:<\/span><\/p>\n Python’da OLS regresyonu nas\u0131l ger\u00e7ekle\u015ftirilir<\/a> Goldfeld-Quandt testi, bir regresyon modelinde heteroskedastisitenin mevcut olup olmad\u0131\u011f\u0131n\u0131 belirlemek i\u00e7in kullan\u0131l\u0131r. De\u011fi\u015fen varyans, bir regresyon modelinde bir yan\u0131t de\u011fi\u015fkeninin farkl\u0131 seviyelerindeki art\u0131klar\u0131n e\u015fit olmayan da\u011f\u0131l\u0131m\u0131n\u0131 ifade eder. E\u011fer heteroskedastisite mevcutsa, bu, do\u011frusal regresyonun, art\u0131klar\u0131n yan\u0131t de\u011fi\u015fkeninin her seviyesinde e\u015fit \u015fekilde da\u011f\u0131ld\u0131\u011f\u0131 y\u00f6n\u00fcndeki temel varsay\u0131mlar\u0131ndan birini ihlal eder. Bu e\u011fitimde Python’da Goldfeld-Quandt testinin nas\u0131l ger\u00e7ekle\u015ftirilece\u011fine […]<\/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-3813","post","type-post","status-publish","format-standard","hentry","category-rehber"],"yoast_head":"\n 1. Ad\u0131m: Veri k\u00fcmesini olu\u015fturun<\/strong><\/h2>\n
import<\/span> pandas as<\/span> pd\n\n#createDataFrame\n<\/span>df = pd. DataFrame<\/span> ({' hours<\/span> ': [1, 2, 2, 4, 2, 1, 5, 4, 2, 4, 4, 3, 6],\n ' exams<\/span> ': [1, 3, 3, 5, 2, 2, 1, 1, 0, 3, 4, 3, 2],\n ' score<\/span> ': [76, 78, 85, 88, 72, 69, 94, 94, 88, 92, 90, 75, 96]})\n\n#view DataFrame\n<\/span>print<\/span> (df)\n\n hours exam score\n0 1 1 76\n1 2 3 78\n2 2 3 85\n3 4 5 88\n4 2 2 72\n5 1 2 69\n6 5 1 94\n7 4 1 94\n8 2 0 88\n9 4 3 92\n10 4 4 90\n11 3 3 75\n12 6 2 96<\/strong><\/pre>\n Ad\u0131m 2: Do\u011frusal regresyon modelini yerle\u015ftirin<\/strong><\/span><\/h2>\n
import<\/span> statsmodels. api<\/span> as<\/span> sm\n\n#define predictor and response variables\n<\/span>y = df[' score<\/span> ']\nx = df[[' hours<\/span> ', ' exams<\/span> ']]\n\n#add constant to predictor variables\n<\/span>x = sm. add_constant<\/span> (x)\n\n#fit linear regression model\n<\/span>model = sm. OLS<\/span> (y,x). fit<\/span> ()\n\n#view model summary\n<\/span>print<\/span> ( model.summary<\/span> ())\n\n OLS Regression Results \n==================================================== ============================\nDept. Variable: R-squared score: 0.718\nModel: OLS Adj. R-squared: 0.661\nMethod: Least Squares F-statistic: 12.70\nDate: Mon, 31 Oct 2022 Prob (F-statistic): 0.00180\nTime: 09:22:56 Log-Likelihood: -38.618\nNo. Observations: 13 AIC: 83.24\nDf Residuals: 10 BIC: 84.93\nModel: 2 \nCovariance Type: non-robust \n==================================================== ============================\n coef std err t P>|t| [0.025 0.975]\n-------------------------------------------------- ----------------------------\nconst 71.4048 4.001 17.847 0.000 62.490 80.319\nhours 5.1275 1.018 5.038 0.001 2.860 7.395\nexams -1.2121 1.147 -1.057 0.315 -3.768 1.344\n==================================================== ============================\nOmnibus: 1,103 Durbin-Watson: 1,248\nProb(Omnibus): 0.576 Jarque-Bera (JB): 0.803\nSkew: -0.289 Prob(JB): 0.669\nKurtosis: 1.928 Cond. No. 11.7\n==================================================== ============================\n<\/strong><\/span><\/pre>\n 3. Ad\u0131m: Goldfeld-Quandt testini ger\u00e7ekle\u015ftirin<\/strong><\/span><\/h2>\n
#perform Goldfeld-Quandt test\n<\/span>sm. stats<\/span> . diagnosis<\/span> . het_goldfeldquandt<\/span> (y, x, drop= 0.2<\/span> )\n\n(1.7574505407790355, 0.38270288684680076, 'increasing')<\/strong><\/pre>\n\n
\n
Sonra ne yapaca\u011f\u0131z<\/strong><\/h2>\n
Ek kaynaklar<\/strong><\/span><\/h2>\n
Python’da Art\u0131k Arsa Nas\u0131l Olu\u015fturulur<\/a>
Python’da White Testi Nas\u0131l Ger\u00e7ekle\u015ftirilir<\/a>
Python’da Breusch-Pagan testi nas\u0131l yap\u0131l\u0131r<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"