English  |  正體中文  |  简体中文  |  Post-Print筆數 : 11 |  Items with full text/Total items : 89671/119468 (75%)
Visitors : 23931738      Online Users : 486
RC Version 6.0 © 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: http://nccur.lib.nccu.edu.tw/handle/140.119/3846


    Title: 台灣地區死亡率模型的理論與實證研究
    Other Titles: A Theoretical and Empirical Study of Mortlity Models in Taiwan Area
    Authors: 余清祥
    Keywords: 死亡率;預測;Lee-Carter 模型;Heligman-Pollard 模型;關係模型;縱斷面;模型生命表
    Mortality Rates;Projection;Lee-Carter Model;Heligman-Pollard Model;Cohort;Relational Model;Model Life Tables
    Date: 2002
    Issue Date: 2007-04-18 16:36:44 (UTC+8)
    Publisher: 臺北市:國立政治大學統計學系
    Abstract: 死亡率的變化關係到社會福利與政策的制訂,尤其是死亡率改善幅度快速的台灣地區,死亡率預測的正確性影響至鉅。然而與多數近年經濟突飛猛進的國家類似,台灣地區的死亡率記錄過去並不完整(例如:1950年代最高年齡組為70 歲,1960 年代為80歲,1980 年代為85 歲,1990 年代為100歲)或有瑕疵(例如:1994 年以前嬰兒死亡率的數字),適用於歐、美、日等已開發國家之死亡率模型不見得適合,由Yue, Hu, and Chang (2001)台灣高齡人口死亡率模型的實證研究可見一斑。本計畫首要目的為比較常見的死亡率模型,包括Lee-Carter、Heligman-Pollard、與關係(Relational)等知名的參數模型,以及縱斷面法與模型生命表等無母數方法,套入台灣地區過去50 年的死亡資料,尋找最符合台灣狀況的0 至100 歲之死亡率模型。實證部分中, 本研究預計使用交叉驗證(Cross-Validation)評定模型的預測優劣;理論部分也將探討如何修正既有的死亡率模型,尋求最佳的估計法,使之能套用至不完整資料。
    Mortality projection plays a critical role in designing social and welfare policies, especially for countries and areas like Taiwan with rapid mortality improvements. However, due to the incomplete data of the elderly mortality and data quality in the earlier days (which are common problems existing in most developing countries), directly applying frequently used methods, such as Lee-Carter and Heligman-Pollard models are highly questionable. See Yue, Hu, and Chang (2001) for a discussion of the mortality rates of elderly in Taiwan. In this study, we will compare some well-known mortality models, including Lee-Carter model, Heligman-Pollard model, Relational model (parametric form), Cohort method, and Model Life Tables (nonparametric form), based on the 1951-2000 Taiwan mortality data, and try to find the method that can describe the mortality characteristics in Taiwan the best. Empirically, we will use cross-validation to judge which method has the best fit. Also, we will seek ways to modify the current methods and improve their estimation in the cases of incomplete data.
    Description: 核定金額:411000元
    Data Type: report
    Appears in Collections:[統計學系] 國科會研究計畫

    Files in This Item:

    File Description SizeFormat
    912412H004005.pdf49KbAdobe PDF1685View/Open


    All items in 政大典藏 are protected by copyright, with all rights reserved.


    社群 sharing

    著作權政策宣告
    1.本網站之數位內容為國立政治大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,惟仍請適度,合理使用本網站之內容,以尊重著作權人之權益。商業上之利用,則請先取得著作權人之授權。
    2.本網站之製作,已盡力防止侵害著作權人之權益,如仍發現本網站之數位內容有侵害著作權人權益情事者,請權利人通知本網站維護人員(nccur@nccu.edu.tw),維護人員將立即採取移除該數位著作等補救措施。
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback