English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 63184/95884 (66%)
造访人次 : 4526388      在线人数 : 329
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜寻范围 查询小技巧:
  • 您可在西文检索词汇前后加上"双引号",以获取较精准的检索结果
  • 若欲以作者姓名搜寻,建议至进阶搜寻限定作者字段,可获得较完整数据
  • 进阶搜寻


    jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/103000


    题名: 遺失資料結構對插補策略應用在不完全長期追蹤資料之影響
    其它题名: The Impact of Missing-Data Mechanisms on Imputation Strategies for Incomplete Longitudinal Data
    作者: 陳怡如
    贡献者: 淡江大學統計學系
    关键词: 不完全長期追蹤資料;非隨機遺失;多重插補法incomplete longitudinal data;not missing at random;multiple imputation
    日期: 2012-08
    上传时间: 2015-05-13 11:19:28 (UTC+8)
    摘要: 遺失資料常發生於長期追蹤研究中,多重插補即為其中一種解決遺失值問題的有效方法。在初期時,多重插補方法主要應用於抽樣調查與普查方面,然而近年來持續擴展應用於生物醫學、行為與社會科學等領域。雖然已有些學者提出處理有關不完全長期追蹤二元資料與不完全長期追蹤順序資料的多重插補法,但是鮮少有討論在不同遺失資料結構下,這些插補策略之表現。遺失資料結構之重要性,在於處理遺失資料方法之特性極度仰賴遺失資料結構。遺失資料結構包含完全隨機遺失、隨機遺失與非隨機遺失。一般而言,實務上較會發生遺失值的情況屬於非隨機遺失。在之前的研究計畫中,已應用模擬研究來探討一些插補策略,就標準化偏誤、均方根誤差與涵蓋率等衡量指標,以瞭解在完全隨機遺失和隨機遺失下之表現。此申請研究計畫之主要研究目標,則是更進一步討論現有的插補策略與研究中的新插補策略,在非隨機遺失情況下之表現。
    Multiple imputation method is one of the effective approaches to solve the problem of missing data which are commonly occurred in longitudinal studies. The initial use of multiple imputation is primarily for sample surveys and censuses. Nowadays, this attractive approach has been increasingly utilized in the biomedical, behavioral, and social sciences. Several imputation strategies have been proposed for dealing with incomplete longitudinal binary or ordinal data. However, few of them discuss the influence of missing-data mechanisms on those imputation strategies. The main reason that missing-data mechanisms are crucial is the properties of missing-data approaches depending very strongly on the mechanisms. Missing-data mechanisms include missing completely at random (MCAR), missing at random (MAR) and not missing at random (NMAR). In the previous project, the performances of some imputation strategies have been evaluated in terms of standardized bias, root-mean-squared error and coverage percentage under MCAR and MAR. The aim of this project is to further investigate the impact of NMAR on the current imputation strategies and the ongoing approach for incomplete longitudinal data, which is more practical in real-life applications.
    显示于类别:[統計學系暨研究所] 研究報告

    文件中的档案:

    没有与此文件相关的档案.

    在機構典藏中所有的数据项都受到原著作权保护.

    TAIR相关文章

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