中大機構典藏-NCU Institutional Repository-提供博碩士論文、考古題、期刊論文、研究計畫等下載:Item 987654321/97957
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 83696/83696 (100%)
Visitors : 56346884      Online Users : 1714
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version


    Please use this identifier to cite or link to this item: https://ir.lib.ncu.edu.tw/handle/987654321/97957


    Title: BDM與強韌概似法在配對有序相關性資料分析中的比較研究;Comparative study of BDM and robust likelihood approach in pairwise ordinal correlated data analysis
    Authors: 張瑜珊;Chang, Yu-Shan
    Contributors: 統計研究所
    Keywords: 強韌概似函數;配對相關性資料;多項分配;Robust likelihood approach;pairwise ordinal correlated data;multinomial distribution
    Date: 2025-06-06
    Issue Date: 2025-10-17 12:12:22 (UTC+8)
    Publisher: 國立中央大學
    Abstract: 配對有序相關性資料常見於生物醫學研究領域,例如,同一家庭中兩個成員的遺傳疾病嚴重程度(無、輕微、中等)可以形成一個3x3的有序列聯表,其中每個單元格子代表來自同家庭的兩個成員各別在特定疼痛程度的觀察次數。
    比例勝算模型(Proportional Odds Model)是常用於分析有序分類資料的迴歸模型,若雙變數反應變數相互獨立時,每個觀測值的條件分佈可以被視為多項分佈,並建立概似函數用以估計迴歸模型中感興趣的參數。但若反應變數間存在相關性時,難以找到適合的分佈描述這樣性質的資料,無法建立聯合分佈,因此需要其他方法來處理這種情境,例如戴爾雙變數模型 (Bivariate Dale Model,以下簡稱BDM)。
    本研究中我們使用強韌化多項分配的概似函數,以及BDM來分析雙變數有序相關性資料,透過模擬研究與實例分析,我們透過簡單迴歸說明當資料不服從BDM時,即使BDM與強韌化概似函數法在感興趣參數的估計上有差不多的表現,但BDM則在捕捉關聯性結構會出現錯誤的統計推論,並且從模擬結果觀察到,若雙變數間存在負關聯性時,BDM中關聯性參數的估計量以及估計量的漸進變異數估計值會對於樣本數很敏感,然而強韌多項概似函數則不會有這個現象。;Pairwise ordinal correlated data are common in biomedical research, such as genetic diseases severity levels (none, mild, moderate) between family members forming a 3x3 ordinal contingency table.
    While independent bivariate responses follow multinomial distributions with straightforward parameter estimation, correlated responses require alternative approaches like the Bivariate Dale Model (BDM).
    This study compares a robust multinomial likelihood approach with BDM for analyzing pairwise ordinal correlated data. Through simulations and empirical analysis, we show that while both methods perform similarly in estimating regression parameters when data don′t follow BDM , the BDM may produce incorrect statistical inference for association structures. Notably, with negative association between variables, BDM′s association parameter estimates and their asymptotic variances show high sensitivity to sample size, a phenomenon not observed with the robust approach.
    Appears in Collections:[Graduate Institute of Statistics] Electronic Thesis & Dissertation

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML2View/Open


    All items in NCUIR are protected by copyright, with all rights reserved.

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 隱私權政策聲明