[問題] 求助統計高手能否幫我解釋這段文章

看板Statistics作者 (補個~幹!)時間11年前 (2012/08/13 21:44), 編輯推噓0(0012)
留言12則, 3人參與, 最新討論串1/1
事情是這樣的 最近在看一篇paprt但是裡面有許多統計的東西 和我所屬的領域有些差異,能否有高手能幫忙解答這段是在說什麼 The reported error for the means is one standard error. (這邊是說,本篇的誤差是在一個標準差內)?? Normality test of each single variable distribution was carried out using Shapiro-Wilk test . (是說使用Shapiro-Wilk test來檢驗這些單獨資料是否成常態分佈)?? In order to test whether patients behaved differently for X, Y, and Z shifts, different statistics were carried out. (為了檢驗是否因為"病人"導致"X,Y,Z位移有不同"的表現,進行了不同的統計分析)?? Using an F-test, Analysis of Variance (ANOVA) was performed to verify that the patient means were statistically different. (使用 F-test變異數分析(ANOVA)驗證病人有無顯著差異) ?? As ANOVA is based on the strong assumption of normality of the underlining random variable, for sake of robustness a non-parametric test (Kruskal-Wallis) was performed to compare medians of each patient (p-value was determined using a χ2 distribution). (由於ANOVA是以常態分布為前提假設...這邊就陷入混亂了..看不懂再幹麻???) The Levene test was carried out to test the equality of variances of each patient through an F-test. ( Levene test 用來測試平等....經由F-test??????) 希望有好心人能出手指導一下 -- ※ 發信站: 批踢踢實業坊(ptt.cc) ◆ From: 111.240.163.94

08/13 21:57, , 1F
倒數第二段是說ANOVA對常態性依賴太重,考量到穩健性
08/13 21:57, 1F

08/13 21:58, , 2F
改用Kruskal-Wallis的無母數統計(類似anova但改用中位數)
08/13 21:58, 2F

08/13 22:02, , 3F
最後一段是說XYZ組別之間的變異數不能差異的太離譜
08/13 22:02, 3F

08/13 22:02, , 4F
所以去檢定變異數同質性,跟之前檢定XYZ的常態性類似
08/13 22:02, 4F

08/13 22:03, , 5F
都是為了說服讀者他做的 F-test 可信,因為這些都是基本假設
08/13 22:03, 5F

08/13 22:04, , 6F
所以作者應該同時有提供Anova&Kruskal-Wallis兩種檢定結果
08/13 22:04, 6F

08/13 22:04, , 7F
看看你是否總之是會相信這樣
08/13 22:04, 7F

08/13 22:51, , 8F
非常感謝樓上的解答~我好像有多一些解了!謝謝
08/13 22:51, 8F

08/14 02:48, , 9F
第一句話: 報告中所列平均數的 "誤差", 是指一倍標準誤.
08/14 02:48, 9F

08/14 02:51, , 10F
後3段, 是在比較什麼看不出來! (研究對象如何分組看不出來.)
08/14 02:51, 10F

08/14 02:53, , 11F
第3句, 沒看上下文不能完全明白. 不過, 句子中提到的是針對
08/14 02:53, 11F

08/14 02:55, , 12F
X, Y, Z 三種指標, 用以分析比較的是採用不同統計量.
08/14 02:55, 12F
文章代碼(AID): #1GAGIuGZ (Statistics)