English  |  正體中文  |  简体中文  |  Items with full text/Total items : 62805/95882 (66%)
Visitors : 3892735      Online Users : 342
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: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/77379

    Title: 廣義混和效用模型有測量誤差時之多種估計方法
    Other Titles: On the estimation methods for the generalized linear mixed effect model with measurement error
    Authors: 余佳倫;Yu, Chia-Lun
    Contributors: 淡江大學數學學系碩士班
    黃逸輝;Huang, Yih-Huei
    Keywords: 測量誤差;混和效用;加權校正分數函數;重複觀測;measurement error;Mixed Effect;Weighted and Corrected Score Function;Replicates
    Date: 2012
    Issue Date: 2012-06-21 06:38:18 (UTC+8)
    Abstract: 當測量誤差(measurement error)和混和效用(mixed effect)同時出現在模型上,文獻上並無太多討論,主因是隨機效用積分後之邊際分配不再是廣義線性模型。本文探討log-linear及logistic模型中有測量誤差及混和效用時之估計方法,在log-linear模型討論常用的測量誤差校正方法包括naive、RC(regression calibration)、SIMEX(simulation extrapolation)、SMEA(small measurement error approximation)外,提出加權校正分數函數,並在重複觀測情況下使用加權、校正再加權之估計方法。而logistic模型除了使用積分取得邊際分配來估計外,利用動差建構估計方程式來估計,在重複觀測下使用部分校正來與未校正作比較。最後用電腦模擬本文所提之估計方法。
    When the measurement error and mixed effect appear in the model at the same time, we can not find much discussion on the literature. The main reason is that the marginal distribution of the integral to the random effect is no longer a generalized linear model. This paper discussed the estimated method between measurement error and mixed effect in the log-linear and logistic model. In the log-linear model, the estimation method usually included naive, regression calibration, simulation extrapolation, small measurement error approximation, and there is another estimation method "Weighted and Corrected Score Function" which is weighted, corrected and weighted again under replication situation. The logistic model in addition to use the integral to obtain the marginal distribution, it also used the moment constructed estimated equation to estimate and compared between partial calibration and without calibration under replication situation. At last, it used the computer to simulate the estimated method which was brought up in this paper.
    Appears in Collections:[Graduate Institute & Department of Mathematics] Thesis

    Files in This Item:

    File SizeFormat

    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