不對稱冪級數GARCH模型之多樣化應用

The Variety Applications in Asymmetric Power GARCH Model

鄒易凭(Yi-Pin Tzou) ； 胡緒寧(Hsu-Ning Hu) ； 鄭婉秀(Wan-Hsiu Cheng)

《東吳經濟商學學報》 63期 (2008/12) Pp. 29-51

https://doi.org/10.29735/SJEB.200812.0002

摘要

本文以不對稱GARCH與不對稱冪級數GARCH兩模型，分析比較新台幣兌換美元匯率、黃金現貨、西德州中級原油現貨與道瓊工業股價指數等四種不同資產報酬率資料之樣本外預測能力。實證結果發現APGARCH確與AGARCH模型有顯著差異，且APGARCH模型對於樣本外之預測能力上也較為準確，證明冪級數條件是影響報酬率波動敏感性不可忽視的重要因素。而在市場不穩定或面臨國際重大事件時，AGARCH模型均會產生估計誤差，包含1991年海灣戰爭、1997年底亞洲金融風暴及1999年9月金價不穩定時，AGARCH模型分別對石油、匯率及黃金現貨報酬有高估現象，而1987年美國股市崩盤、1997年亞洲金融風暴、2001年911事件等事件，AGARCH在估計道瓊股價指數報酬波動時則明顯低估。

關鍵字

冪級數GARCH模型 ； 波動

並列摘要

This paper investigates spot volatilities in various spot markets, including WTI crude oil, gold, exchange rate of NT dollars to US dollars, and Dow Jones Industrial Average stock index, using Asymmetric power GARCH model. This paper also uses the out-of-sample estimation for the parameter of power. The empirical results find that the parameter is different from two, the assumption in Asymmetric GARCH model. It is indicated that the power transformation is an essential factor in volatility estimation. Therefore, the estimation errors would appear in Asymmetric GARCH model, especially the great events occurring. This paper finds that the GARCH model would bias the estimation during the Gulf War, Asian financial crisis and the 911 event periods, and the PGARCH model can capture the volatilities more appropriately.

並列關鍵字

Asymmetric Power GARCH model ； Volatility

參考文獻

Anè, T.(2005).Do Power GARCH Models Really Improve Value-at-Risk Forecasts?.Journal of Economics and Finance.29,337-358.

Bail, Turan G.(2007).Modeling the Dynamics of Interest Rate Volatility with Skewed Fat Tailed Distributions.Annals of Operations Research.151(1),151-178.

Bera, A. K.,M. L. Higgins(1993).ARCH Models: Properties, Estimation and Testing.Journal of Economic Surveys.4,305-362.

Bollerslev, T.(1986).Generalized Autoregressive Conditional Heteroscedasticity.Journal of Econometrics.31,307-327.

Bollerslev, T.,R. F. Engle,D. B. Nelson (edited),D. I. McFadden(1994).Handbook of Econometrics.Amsterdam:North-Holland.