<\/p>\n
Basit bir do\u011frusal regresyon<\/a> ger\u00e7ekle\u015ftiririz ve a\u015fa\u011f\u0131daki tahmini regresyon denklemini elde ederiz:<\/span><\/p>\n \u0177 = b 0<\/sub> + b 1<\/sub> x<\/span><\/strong><\/p>\n Genellikle e\u011fim katsay\u0131s\u0131 b 1’in<\/sub> istatistiksel olarak anlaml\u0131 olup olmad\u0131\u011f\u0131n\u0131 bilmek isteriz.<\/span><\/p>\n b1’in<\/sub> istatistiksel olarak anlaml\u0131 olup olmad\u0131\u011f\u0131n\u0131 belirlemek i\u00e7in a\u015fa\u011f\u0131daki test istatisti\u011fiyle bir t-testi yapabiliriz:<\/span><\/p>\n t = b 1<\/sub> \/ se(b 1<\/sub> )<\/span><\/strong><\/p>\n Alt\u0131n:<\/span><\/p>\n Daha sonra bu test istatisti\u011fine kar\u015f\u0131l\u0131k gelen p de\u011ferini<\/a> n-2 serbestlik derecesiyle hesaplayabiliriz.<\/span><\/p>\n E\u011fer p de\u011feri belli bir e\u015fikten k\u00fc\u00e7\u00fckse (\u00f6rne\u011fin \u03b1 = 0,05), e\u011fim katsay\u0131s\u0131n\u0131n s\u0131f\u0131r olmad\u0131\u011f\u0131 sonucuna varabiliriz.<\/span><\/p>\n Ba\u015fka bir deyi\u015fle, yorday\u0131c\u0131 de\u011fi\u015fken ile modeldeki yan\u0131t de\u011fi\u015fkeni<\/a> aras\u0131nda istatistiksel olarak anlaml\u0131 bir ili\u015fki vard\u0131r.<\/span><\/p>\n A\u015fa\u011f\u0131daki \u00f6rnek, R’deki bir regresyon \u00e7izgisinin e\u011fimi i\u00e7in t testinin nas\u0131l ger\u00e7ekle\u015ftirilece\u011fini g\u00f6sterir.<\/span><\/p>\n R’de, bir s\u0131n\u0131ftaki 12 \u00f6\u011frencinin ald\u0131\u011f\u0131 ders saatleri ve final s\u0131nav puanlar\u0131 hakk\u0131nda bilgi i\u00e7eren a\u015fa\u011f\u0131daki veri \u00e7er\u00e7evesine sahip oldu\u011fumuzu varsayal\u0131m:<\/span><\/p>\n \u00c7al\u0131\u015f\u0131lan saatlerle s\u0131nav puanlar\u0131 aras\u0131nda istatistiksel olarak anlaml\u0131 bir ili\u015fki olup olmad\u0131\u011f\u0131n\u0131 belirlemek i\u00e7in basit bir do\u011frusal regresyon modeli uygulamak istedi\u011fimizi varsayal\u0131m.<\/span><\/p>\n Bu regresyon modeline uymak i\u00e7in R’deki lm()<\/a> fonksiyonunu kullanabiliriz:<\/span><\/p>\n Model sonu\u00e7lar\u0131ndan tahmin edilen regresyon denkleminin \u015fu \u015fekilde oldu\u011funu g\u00f6rebiliriz:<\/span><\/p>\n S\u0131nav puan\u0131 = 67,7685 + 2,7037 (saat)<\/span><\/p>\n E\u011fim katsay\u0131s\u0131n\u0131n istatistiksel olarak anlaml\u0131 olup olmad\u0131\u011f\u0131n\u0131 test etmek i\u00e7in t-testi istatisti\u011fini a\u015fa\u011f\u0131daki \u015fekilde hesaplayabiliriz:<\/span><\/p>\n Bu t-testi istatisti\u011fine kar\u015f\u0131l\u0131k gelen p de\u011feri, \u00e7\u0131kt\u0131da Pr(> |t|)<\/strong> ad\u0131 verilen s\u00fctunda g\u00f6r\u00fcnt\u00fclenir.<\/span><\/p>\n P de\u011feri 0,00464<\/strong> olarak \u00e7\u0131k\u0131yor.<\/span><\/p>\n Bu p de\u011feri 0,05’ten k\u00fc\u00e7\u00fck oldu\u011fundan e\u011fim katsay\u0131s\u0131n\u0131n istatistiksel olarak anlaml\u0131 oldu\u011fu sonucuna var\u0131yoruz.<\/span><\/p>\n Yani \u00f6\u011frencinin ders saati say\u0131s\u0131 ile \u00f6\u011frencinin s\u0131navda ald\u0131\u011f\u0131 final notu aras\u0131nda istatistiksel olarak anlaml\u0131 bir ili\u015fki vard\u0131r.<\/span><\/p>\n A\u015fa\u011f\u0131daki e\u011fitimlerde R’de di\u011fer ortak g\u00f6revlerin nas\u0131l ger\u00e7ekle\u015ftirilece\u011fi a\u00e7\u0131klanmaktad\u0131r:<\/span><\/p>\n R’de basit do\u011frusal regresyon nas\u0131l ger\u00e7ekle\u015ftirilir<\/a> Basit bir do\u011frusal regresyon ger\u00e7ekle\u015ftiririz ve a\u015fa\u011f\u0131daki tahmini regresyon denklemini elde ederiz: \u0177 = b 0 + b 1 x Genellikle e\u011fim katsay\u0131s\u0131 b 1’in istatistiksel olarak anlaml\u0131 olup olmad\u0131\u011f\u0131n\u0131 bilmek isteriz. b1’in istatistiksel olarak anlaml\u0131 olup olmad\u0131\u011f\u0131n\u0131 belirlemek i\u00e7in a\u015fa\u011f\u0131daki test istatisti\u011fiyle bir t-testi yapabiliriz: t = b 1 \/ se(b 1 ) Alt\u0131n: […]<\/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-4151","post","type-post","status-publish","format-standard","hentry","category-rehber"],"yoast_head":"\n\n
\u00d6rnek: R’deki regresyon \u00e7izgisinin e\u011fimi i\u00e7in bir t testi \u00e7al\u0131\u015ft\u0131rma<\/strong><\/span><\/h2>\n
#create data frame\n<\/span>df <- data. frame<\/span> (hours=c(1, 1, 2, 2, 3, 4, 5, 5, 5, 6, 6, 8),\n score=c(65, 67, 78, 75, 73, 84, 80, 76, 89, 91, 83, 82))\n\n#view data frame\n<\/span>df\n\n hours score\n1 1 65\n2 1 67\n3 2 78\n4 2 75\n5 3 73\n6 4 84\n7 5 80\n8 5 76\n9 5 89\n10 6 91\n11 6 83\n12 8 82<\/strong><\/pre>\n #fit simple linear regression model\n<\/span>fit <- lm(score ~ hours, data=df)\n\n#view model summary\n<\/span>summary(fit)\n\nCall:\nlm(formula = score ~ hours, data = df)\n\nResiduals:\n Min 1Q Median 3Q Max \n-7,398 -3,926 -1,139 4,972 7,713 \n\nCoefficients:\n Estimate Std. Error t value Pr(>|t|) \n(Intercept) 67.7685 3.3757 20.075 2.07e-09 ***\nhours 2.7037 0.7456 3.626 0.00464 ** \n---\nSignificant. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1\n\nResidual standard error: 5.479 on 10 degrees of freedom\nMultiple R-squared: 0.568, Adjusted R-squared: 0.5248 \nF-statistic: 13.15 on 1 and 10 DF, p-value: 0.004641\n<\/strong><\/pre>\n\n
Ek kaynaklar<\/strong><\/span><\/h2>\n
R’de \u00e7oklu do\u011frusal regresyon nas\u0131l ger\u00e7ekle\u015ftirilir<\/a>
R’de regresyon \u00e7\u0131kt\u0131s\u0131 nas\u0131l yorumlan\u0131r<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"