English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 55523/89843 (62%)
造訪人次 : 10960897      線上人數 : 197
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋
    請使用永久網址來引用或連結此文件: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/46954


    題名: 廣義線性混合效用測量誤差模式中的條件分數估計法
    其他題名: The Conditional Score in the Generalized Linear Mixed Measurement Error Model.
    作者: 黃逸輝
    貢獻者: 淡江大學數學學系
    關鍵詞: 長期追蹤資料;族群資料;隨機效用;測量誤差;條件分數;longitudinal data;Clustered data;Random effect;Measurement error;Conditional score
    日期: 2009
    上傳時間: 2010-04-15 15:40:28 (UTC+8)
    摘要: 對於分析長期追蹤資料或族群資料時,某些應變數之間並非是獨立分布的,此時可在迴歸模式中加入隨機效用來說明相關性。本計畫將探討廣義線性混合效用測量誤差模式(GLMMeM)的參數估計,雖然已有一般常用於分析測量誤差模式的統計分法例如迴歸校正,模擬外插或是校正分數函數被應用在相關的問題, 包含線性及廣義線性的混合效用模式(mixed effect model),但卻沒有使用條件分數函數於GLMMeM上的相關討論,然而在沒有隨機效用的廣義線性測量誤差模式上,除了計算可能較複雜以外,條件分數函數所需的假設不強而且結果經常較其它方法精準,因此我們也預期條件分數函數在GLMMeM上也會有相同的優點,值得發展。 In analyzing a longitudinal data or clustered data, one can introduce the random effect components into the regression model to account for the correlation between the individuals within the subgroup. In this project, we consider the estimation of the generalized linear mixed model when the covariate is subject to measurement error which is abbreviated to GLMMeM (Generalized Linear Mixed Measurement error Model). Some conventional approaches in the context of measurement error model, for example, “Regression calibration” , “SIMEX” and “Corrected score” had been applied to GLMMeM with distributional assumptions on the miss-measured covariate. However, the conditional score approach usually performs better than these methods in a fixed effect measurement error model, besides, the conditional score may require less assumptions about the distribution of miss-measured covariate. Thus, it is worthwhile to develope a conditional score estimation in the GLMMeM problem for it may perform better in the GLMMeM than the existent methods.
    顯示於類別:[數學學系暨研究所] 研究報告

    文件中的檔案:

    沒有與此文件相關的檔案.

    在機構典藏中所有的資料項目都受到原著作權保護.

    TAIR相關文章

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - 回饋