原油價格波動性預測

機構典藏 > College of Business and Management > Graduate Institute & Department of Banking and Finance > Thesis > Item 987654321/31652

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/31652

Title:	原油價格波動性預測
Other Titles:	Forecasting the volatility of crude oil price
Authors:	陳佳琪;Chen, Chia-chi
Contributors:	淡江大學財務金融學系碩士班李命志;Lee, Ming-chih
Keywords:	峰態;偏態;預測;GARCH;GJR;SGT;Leptokurtosis;Skewness;Forecasting
Date:	2008
Issue Date:	2010-01-11 01:05:58 (UTC+8)
Abstract:	本文研究西德州原油日報酬的波動性，第一部分以對稱性的GARCH模型及波動不對稱的GJR─GARCH模型均架構於一般化誤差分配（GED）及常態分配進行比較，檢視何者為最佳波動性預測模型。實證結果顯示以西德州原油日報酬為研究標的時，GJR GARCH─GED模型的預測能力較佳。第二部分以實證結果顯示偏態一般化t分配（SGT分配）的配適能力較一般化t分配（GT分配）、偏態t分配（ST分配）、對稱t分配（t分配）和常態分配為佳，亦即當金融資產報酬率存在高峰態與厚尾現象時，偏態一般化t分配（SGT分配）不僅可以解決常態分配所無法捕捉到的厚尾現象，亦可修正一般化t分配（GT分配）與對稱t分配（t分配）無偏態的缺點，對於資產報酬率波動性之設定，比過去常使用的常態分配與對稱的分配更為適當。 This research introduces the volatility of West Texas Intermediate daily return. In part one, in order to test which model is the best, we compared the differences among GARCH-Normal, GARCH-GED, GJR GARCH-Normal and GJR GARCH-GED model. The empirical results indicate that GJR GARCH-GED model can forecast the volatility of West Texas Interemdiate daily return well. In part two, the empirical results indicate that the predictive ability of SGT is much better than GT、ST、t and Normal distribution. SGT can correct not only fat-tailed property, but also defects the low kurtosis of GT and t distribution. For the volatility of asset return setting, the assumption of volatility of assets price is more appropriate than Normal and asymmetric distribution which was often used.
Appears in Collections:	[Graduate Institute & Department of Banking and Finance] Thesis

Files in This Item:

File	Size	Format
	0Kb	Unknown	344	View/Open

Loading...