查詢結果分析
來源資料
頁籤選單縮合
題 名 | 美元外匯風險值評估--兼論GARCH估計模型之問題=Foreign Exchange Value-at-Risk--And the Possible Problem of GARCH Model |
---|---|
作 者 | 洪明欽; 王德仁; | 書刊名 | 統計與資訊評論 |
卷 期 | 6 2000.09[民89.09] |
頁 次 | 頁17-31 |
分類號 | 563.2 |
關鍵詞 | 風險值; Riskmetrics模型; GARCH模型; 拔靴複製法; Value-at-Risk; VaR; Riskmetrics model; GARCH model; Bootstrap; |
語 文 | 中文(Chinese) |
中文摘要 | 由於金融商品不斷地創新,新的金融工具比過去更為複雜,管理者欲了解企業整體的風險是越來越困難。自從 G30、BIS 等權威機構推薦風險值作為量化市場風險的方法後,風險值已成為現今市場風險管理的重要工具。本研究以美元對台幣匯率為實證對象,評比不同模型估計出的風險值與預測績效。本研究所使用的模型包括 J.P. Morgan 的兩個 Riskmetrics 模型、含有異質變異的 GARCH 模型以及無母數的拔靴複製法。本研究得到結論包括:(1) GARCH 模型在短天期外匯標的風險值估計表現很好,然而在長天期風險值有反應過度(不合理高估)的現象。(2) 拔靴複製法所算出的風險值大多呈現平坦走勢,並不會因短期的資料變化而有大幅的調整。 |
英文摘要 | As the commercial products are continuously renovated, new financial instruments are more complicated than ever. It is hard for managers to get the whole picture of risks in business. Since the authoritative organizations, such as G30 and BIS, recommend the Value-at-Risk (VaR) as a way to quantify marketing risks, VaR has recently became an important tool on market risk management. This research takes NT$/US$ exchange rate as our empirical data. It also compares the VaR and predicting effectiveness for different models. The models we discussed consist of two J.P. Morgan's Riskmetrics models(SMA and EWMA)、 GARCH model and non-parametric bootstrap method. Our conclusions include (1) GARCH model performs well in short-holding periods. However, it unreasonably overestimates in long-holding periods. (2) Overall, Value at Risk computed by Bootstrap method performs stable. |
本系統中英文摘要資訊取自各篇刊載內容。