本篇研究欲利用Kawakatsu (2006)所推展出多變量Matrix Exponential GARCH(ME-GARCH)來從事避險,並引用諸如BEKK-GARCH、VC-GARCH及CC-GARCH等多變量的時間序列模型從事避險績效比較,同時也加入基差與不對稱正負基差兩種效果,觀察加入兩種基差效果前後其績效改善的狀況;本文使用1998年到2007年期間中的指數期貨商品從事避險,其資料來源皆取自於DATASTREAM 資料庫;依據實證結果指出,發現在加入傳統基差效果後,大多能提升其模型之避險績效,且四個模型中以ME-GARCH模型之樣本外避險績效最佳,所以建議避險者在挑選模型以從事期貨避險時,可將ME-GARCH模型做為提升避險績效之選擇。
The purpose of this paper is to apply the Matrix Exponential multivariate Generalized Autoregressive Conditional Heteroscedasticity (ME-GARCH) proposed by Kawakatsu (2006) for futures hedging and compare the hedging effectiveness with BEKK-GARCH、VC-GARCH and CC-GARCH models under basis effects and asymmetric positive and negative spreads. This paper investigates index futures contracts collected from DATASTREAM over the period from 1998 to 2007. Based on our research, we find traditional basis effects could improve hedging effectiveness more than asymmetric positive and negative spreads. We also find ME-GARCH with basis effects outperforms BEKK-GARCH、VC-GARCH and CC-GARCH out-of-sample in terms of variance reduction. Therefore, we suggest ME-GARCH with basis effects an alternative for hedgers to improve their hedging effectiveness.