基於Copula 之貝氏方法的比較兩診斷測試之整合性分析;A Bayesian-copula-based approach for meta-analysis of studies comparing two diagnostic tests

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/89646

Title:	基於Copula 之貝氏方法的比較兩診斷測試之整合性分析;A Bayesian-copula-based approach for meta-analysis of studies comparing two diagnostic tests
Authors:	黃子恒;Huang, Tz-Heng
Contributors:	統計研究所
Keywords:	整合性分析;貝氏方法;耦合;貝它二項式分布;DIC;可信區間;診斷測試;馬可夫鏈蒙地卡羅;Meta-analysis;Bayesian approach;copula;beta-binomial distributions;DIC;credible interval;diagnostic test;MCMC
Date:	2022-09-21
Issue Date:	2022-10-04 11:50:50 (UTC+8)
Publisher:	國立中央大學
Abstract:	診斷研究的整合性分析已被廣泛用在生物醫學領域上，而基於Copula 之貝氏方法是被所提倡在比較兩診斷測試的整合性分析中，在控制異質性跟相關性下，我們使用四維度之Copula 模型來彙整診斷測試中的靈敏度跟特異度，特別地說，針對兩診斷測試中真陽性跟真陰性的人數，假設他們的邊際分布為貝它二項式的結構，以及藉由Copula方法來獲得聯合分布。其中，對於有興趣的參數，我們使用貝氏馬可夫鏈蒙地卡羅來做估計，最後，我們透過兩筆不同的診斷測試跟模擬研究來呈現所提出的方法。;Meta-analysis of diagnostic studies is widely used in biomedical research. A Bayesiancopula- based approach is proposed for meta-analysis of studies comparing two diagnostic tests. We use a quadrivariate copula model to pool the sensitivities and specificities of the two diagnostic tests across studies while controlling heterogeneity and correlations. Specifically, the marginal distribution of the numbers of true positive and true negative for the two diagnostic tests of each study is assumed to be beta binomial and the joint distribution is then obtained via copula methods. The parameters of interest are estimated using the Bayesian MCMC approaches. We assess the performance of the proposed method by simulations and two different mata-analysis data.
Appears in Collections:	[Graduate Institute of Statistics] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	130	View/Open

社群 sharing

Loading...