English  |  正體中文  |  简体中文  |  Items with full text/Total items : 49925/85107 (59%)
Visitors : 7779548      Online Users : 33
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/987654321/17319


    Title: 水文短序列模式預測之研究
    Other Titles: Studies on the forecasting for short hydrological time series
    Authors: 虞國興;金士凱
    Contributors: 淡江大學水資源及環境工程學系
    Keywords: 時間序列;河川流量;自相關變異數;部份自迴歸模式;Time Series;Stream Flow;Autocovariance;Subset Autoregressive Model
    Date: 1998-12-22
    Issue Date: 2009-08-04 14:43:19 (UTC+8)
    Abstract: 近來, Hurvich和Tsai(1997)針對短時間序列, 以最小均方預測誤差建立Z/sub t+h/與{Z/sub t-k+1/, ..., Z/sub t/}之線性關係, 提升其預測能力。然其研究僅侷限於某些特殊模式之合成資料, 故本研究將探討Hurvich和Tsai所提方法之適用範圍, 同時亦針對台灣河川月流量資料做一整體性探討。本研究比較Hurvich和Tsai所提方法與傳統時間序列模式於定常性及接近非定常性序列上預測能力之差異,研究中在Hurvich和Tsai方法時, 採用Burg(1978)與傳統兩種推估自相關變異數之方法推求參數。 結果顯示, 就合成資料而言, 利用Burg所提之自相關變異數推估法, 無論對接近非定常性或定常性模式, 其參數推估精確度皆較利用傳統自相關變異數推估法為優; 當模式為接近非定常性模式時, Hurvich和Tsai利用Burg所提之自相關變異數推估法之預測能力均優於傳統時間序列預測方法, 然當模式為定常性時, 本研究所引用之 Hurvich和Tsai方法與時間序列方法, 其預測結果相差不大。實測資料預測結果, 以Hurvich和Tsai利用傳統自相關變異數法之預測能力表現最優, 但SAR模式與Hurvich和Tsai利用傳統自相關變異數兩者預測能力相當, 如考慮參數之精簡原則, 則以SAR模式較為適用於台灣河川月流量資料。
    Recently, Hurvich-Tsai (1997) employed the minimizing the mean squared error to establish the linear relationship between Z/sub t+h/ and {Z/sub t-k+1/,...,Z/sub t/} in order to increase the forecasting abilities for short time series. However, Hurvich-Tsai's research is only limited on analyzing the synthetic data of some specified models. Therefore, the following study is not only probing into the suitable range for Hurvich-Tsai method, but also investigating the monthly riverflow discharge data of Taiwan. In this study, the forecasting abilities of Hurvich- Tsai and the traditional time series models are compared for the data obeying stationarity and non-stationarity. For Hurvich-Tsai method, Burg (1978) and the traditional method for estimating the autocovariance were used to estimate the predictor parameters. The results of synthetic data show that Burg method has better parameters estimating accuracy than traditional method, whatever the data is close to non-stationarity or stationarity with small sample size. For the data close to non-stationarity, the Burg method has better forecasting ability than traditional time series model. When the data is stationary, the forecasting ability of both Hurvich-Tsai and traditional methods are very similar. In general, Hurvich-Tsai with the traditional method for estimating the autocovariance has the better forecasting ability for the real data. However, the SAR model and Hurvich-Tsai with the traditional method for estimating the autocovariance have the same accuracy of predication. The SAR model is better for the monthly riverflow data of Taiwan if the principle of parsimony of the parameter is considered.
    Relation: 八十七年度農業工程研討會論文集,頁 141-148
    Appears in Collections:[水資源及環境工程學系暨研究所] 會議論文

    Files in This Item:

    File Description SizeFormat
    水文短序列模式預測之研究_中文摘要.docx摘要17KbMicrosoft Word54View/Open
    水文短序列模式預測之研究_英文摘要.docx摘要19KbMicrosoft Word65View/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