English  |  正體中文  |  简体中文  |  Items with full text/Total items : 49292/83829 (59%)
Visitors : 7160378      Online Users : 80
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU 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: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/87471


    Title: 廣義線性模型中之延伸校正分數函數
    Other Titles: Extended corrected-score in generalized linear models
    Authors: 楊喬閔;Yang, Chiao-Min
    Contributors: 淡江大學數學學系碩士班
    黃逸輝;Huang, Yih-Huei
    Keywords: 測量誤差;校正分數;條件分數;延伸校正分數;誤差增量;measurement error;Corrected score;Conditional score;extended corrected-score;error augmentation
    Date: 2012
    Issue Date: 2013-04-13 11:11:13 (UTC+8)
    Abstract: 當迴歸模型中的自變數有測量誤差時,有兩個常用的估計方法:校正分數 (Corrected Score) 以及條件分數 (Conditional Score),但此兩種方法所需的假設條件限制了能應用的迴歸模型。在此我們提出延伸校正分數(Extended corrected-score),它是利用兩個重複量測,將分數函數加權,使之易於找到不偏估計式,加以校正,最後再次加權,進而得到延伸校正分數函數。另外在沒有重複量測時,我們提出誤差增量方法 (Error Augmentation),來提供所需的兩個替代變數。
    When the covariates are measured with errors in a regression model, there are two major consistent estimation methods: the corrected score and the conditional score. Though these methods work well when applicable, there are many models for which there is no corrected score or conditional score. We propose an estimation method named extended corrected-score that has a wider range of applicable models. Our estimation method was developed based on the availability of replicates. When there is no replicate, we propose an error augmentation technique to generate two surrogates, and our extended corrected-score is applicable again.
    Appears in Collections:[數學學系暨研究所] 學位論文

    Files in This Item:

    File SizeFormat
    index.html0KbHTML68View/Open

    All items in 機構典藏 are protected by copyright, with all rights reserved.


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