在區間設限資料下之威爾寇克遜檢定 = Wilcoxon Rank Sum...
國立高雄大學統計學研究所

 

  • 在區間設限資料下之威爾寇克遜檢定 = Wilcoxon Rank Sum Test for Interval Censored Data
  • Record Type: Language materials, printed : monographic
    Paralel Title: Wilcoxon Rank Sum Test for Interval Censored Data
    Author: 黃怡萱,
    Secondary Intellectual Responsibility: 國立高雄大學
    Place of Publication: [高雄市]
    Published: 撰者;
    Year of Publication: 2014[民103]
    Description: 51面圖,表 : 30公分;
    Subject: 長期追蹤數據
    Subject: longitudinal data
    Online resource: http://handle.ncl.edu.tw/11296/ndltd/97475249935454187455
    Notes: 105年10月25日公開
    Notes: 參考書目:面45-46
    Summary: 定期追蹤之長期追蹤數據(longitudinal data)是醫學上常見的資料型態。以比較兩種不同藥物對肝臟腫瘤抑制能力為例,隨機分配前先檢測受試者腫瘤大小,再要求受試者用藥後定期回診,並於每次回診檢測腫瘤大小。若欲比較兩種藥物使用後腫瘤成長至1.5倍之時間,由於試驗設計之侷限無法觀測到確實時間(exact failure time),故假定受試者皆定期回診,依然可考慮以威爾寇克遜檢定(Wilcoxon rank sum test)檢定之。但若受試者因故而無法定期回診,則威爾寇克遜檢定不適合直接使用。我們針對此一問題,提出威爾寇克遜檢定之推廣並以實際例子做分析。 Wilcoxon rank sum test is a useful nonparametric method for testing the equality of distribution of two populations. It has greater efficiency than the t-test on heavy tail distribution, and is nearly as efficient as the t-test on normal distribution. In this paper, an extension of Wilcoxon test for interval censored data which are often found in longitudinal studies is provided. A series of simulation is given to show the performance of the proposed method and the power of our proposed test is better than Finkelstein (1986) and Sun (1996) in some circumstance. We also use our proposed teat to analyze three examples and show the results.
Items
  • 2 records • Pages 1 •
 
310002634254 博碩士論文區(二樓) 不外借資料 學位論文 TH 008M/0019 343201 4494 2014 一般使用(Normal) On shelf 0
310002634262 博碩士論文區(二樓) 不外借資料 學位論文 TH 008M/0019 343201 4494 2014 c.2 一般使用(Normal) On shelf 0
  • 2 records • Pages 1 •
Reviews
Export
pickup library
 
 
Change password
Login