二元配對資料下根據條件勝算比建構之正確非劣性檢定; Exact non-inferiority test based on conditional odds ratio for matched-pair data

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/43890

Title:	二元配對資料下根據條件勝算比建構之正確非劣性檢定;Exact non-inferiority test based on conditional odds ratio for matched-pair data
Authors:	李庭慧;Ting-Huei Li
Contributors:	統計研究所
Keywords:	條件勝算比;正確信賴界限;二元配對資料;干擾參數;非劣性檢定;Buehler 方法;exact confidence bounds;conditional odds ratio;Buehler method;nuisance parameter;noninferiority test;binary matched-pair data
Date:	2010-07-22
Issue Date:	2010-12-08 14:24:29 (UTC+8)
Publisher:	國立中央大學
Abstract:	本文考慮根據條件勝算比針對二元配對資料進行受測和對照處理的非劣性檢定。首先利用已有的近似檢定推導此一勝算比的近似信賴界限，但是這些近似信賴界限的最小覆蓋機率低於名目信賴水準。本文進一步利用Buehler (1957)的方法修正上述的近似信賴界限，得到條件勝算比的正確信賴界限，並且得到兩種處理的正確非劣性檢定。本文計算上述非劣性檢定的型I誤差率和檢定力，評估近似及正確非劣性檢定的表現。最後，利用一筆資料說明所提正確非劣性檢定的應用。 This article considers testing against the noninferiority of a testing treatment to a reference treatment based on the conditional odds ratio for matched-pair data. Approximated confidence bounds for the odds ratio are first derived from existed approximate tests. However, the minimum coverage probabilities of the approximate confidence bounds lose to maintain their nominal level. Therefore, the approximate confidence bounds are modified based on the results in Buehler (1957), and the exact noninferiority tests are obtained. The type I error rates and power are then computed to evaluate the performance of the approximate and exact noninferiority tests. Finally, the exact tests are illustrated by using a real data set.
Appears in Collections:	[Graduate Institute of Statistics] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	771	View/Open

社群 sharing

Loading...