教師資料查詢 | 類別: 會議論文 | 教師: 林允永 LIN YUN-YUNG (瀏覽個人網頁)

標題:價格跳躍下的風險值的計算
學年92
學期2
發表日期2004/05/21
作品名稱價格跳躍下的風險值的計算
作品名稱(其他語言)Value at Risk under Price Jump Risk
著者林允永; 洪瑞成; 邱建良; 林柏青
作品所屬單位淡江大學財務金融學系
出版者
會議名稱2004財經政策與財務工程研討會=Conference on Financial and Economic Policies and Financial Engineering
會議地點臺北市, 臺灣
摘要本篇文章採用Maheu and McCurdy (2003)所提出GARJI模型和GARCH模型估算布蘭 特原油期貨、S&P500指數現貨與美國30年期公債期貨之風險值。由於GARJI模型 可反應市場對於非預期的新訊息所造成的衝擊且具有較好的樣本外波動預測能力 ,因此本文利用GARJI模型捕捉此不連續的狀態,並將此不連續的情形納入計算 風險值的過程中,同時將偏態係數納入百分位數的修正。由實證結果可知,在通 過回溯測試的前提下,GARJI的穿透率和RMSE均較GARCH模型低,因此其風險管理 的績效較GARCH模型優異,而在壓力測試上也有佳的表現。;In this paper, we employ the GARJI model, proposed by Maheu and McCurdy (2003), and GARCH model to estimate the Value-at-Risk (VaR) of Brent oil futures、S&P500 index and 30-year US Treasury Bond futures. The GARJI model captures not only occasional large changes in price, which due to the impact of unexpected news arrivals, but also has better forecasting ability of out-of-sample volatilities. We adopt the GARJI model to grasp this effect and adjust the percentile of skewness coefficient. At last, we bring it into the computation of VaR. From the empirical results, we find that the GARJI model, as viewpoints of failure rate and RMSE, has better risk management performance than GARCH model and it also performs better than GARCH model in Stress-Testing.
關鍵字GARJI模型;風險值;布蘭特原油期貨;S&P500指數現貨;美國30年期公債期貨;GARJI model;Value at risk;Brent oil futures;S&P500 index;30-yearUS Treasury Bond futures
語言中文
收錄於
會議性質國內
校內研討會地點
研討會時間20040521~20040521
通訊作者
國別中華民國
公開徵稿Y
出版型式紙本
出處2004財經政策與財務工程研討會論文集=Proceedings of Conference on Financial and Economic Policies and Financial Engineering,36頁
相關連結
Google+ 推薦功能,讓全世界都能看到您的推薦!