English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  Items with full text/Total items : 110944/141864 (78%)
Visitors : 48024167      Online Users : 919
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
    Home ‧ Login ‧ Upload ‧ Help ‧ About ‧ Administer Goto mobile version


    Please use this identifier to cite or link to this item: https://nccur.lib.nccu.edu.tw/handle/140.119/3794


    Title: 實質匯率預測：TAR與AR之比較
    Other Titles: Forcasting Real Exchange Rate Out-of-sample: TAR vs. AR
    Authors: 郭炳伸
    Keywords: 實質匯率;預測;門檻迴歸模型;自動迴歸模型
    Real exchange rate;Forecasting;Threshold autoregressive model;Autoregressive mode
    Date: 2001
    Issue Date: 2007-04-18 16:36:11 (UTC+8)
    Publisher: 臺北市：國立政治大學國際貿易學系
    Abstract: We set out to compare the out-of-sample forecasting performance of a linear AR model and a nonlinear TAR model. The idea was to see if the intuitively appealing suggestion of nonlinear adjustment of real exchange rates toward purchasing power parity, due to market frictions, could be utilized in forecasting. Indeed, we found the tendency of the US/DEM real exchange rate to converge faster when the previous real exchange rate was farther away from the estimated purchasing power parity level. However, this tendency did not appear to be strong enough for the TAR specification to lead to consistently better out-of-sample forecasting performance. One reason may be that the data sample is not long enough to reliably estimate the non-linear specification which requires more parameters to be estimated than the more parsimonious linear specification. The results presented in this paper are very preliminary. The next step we want to pursue is to check the robustness of the results to the assumption on the inner regime process. Specifically, we want to a restrict the inner regime to follow a unit root process. This is reasonable given that the estimated inner regime does not appear mean reverting. Also, we would like to tackle the forecast uncertainty further. Recently, Kitamura (1999) has paid attention to the uncertainty involved in the coefficient estimates and the resulting risk involved in the forecasts. He suggests using bootstrap smoothing to reduce the variance of the forecasts. The intuition is that since the forecast is sensitive to the realization of training period samples, its variance is reduced by first perturbing the training observations using the bootstrap and then averaging over the perturbed series. Following this idea we intend to combine bootstrapping with the MC forecasting hoping to reduce the variations in the TAR forecasts and thus potentially improve their overall accuracy. Also, we want to check for the robustness of the results for the assumptions about the error process. Doing the estimations for other currencies would help in gaining some understanding of the generality of the results as well. If our current results are found to hold with these robustness checks, we would conclude that the theoretically and intuitively attractive idea behind the nonlinear threshold adjustment may not be empirically significant enough to help us in understanding the future behavior of real exchange rates.
    Description: 核定金額：800100元
    Data Type: report
    Appears in Collections:[國際經營與貿易學系 ] 國科會研究計畫

    Files in This Item:

    File Description SizeFormat
    902415H004013.pdf137KbAdobe PDF21446View/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 Copyright Announcement
    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。
    The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

    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。
    NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback