标题: 利用CCC与DCC模型估算能源期货最适避险比率
Optimal Hedge Ratio of Energy Futures Using CCC and DCC Models
作者: 翁妮铃
Ni-Ling Weng
周雨田
Ray Yeutien Chou
经营管理研究所
关键字: 能源期货;CCC;DCC;GARCH;CARR;最适避险比率;Energy futures;CCC;DCC;GARCH;CARR;Optimal hedge ratio
公开日期: 2006
摘要:   由于能源商品不同于其他农产品商品的不可再生独特性,辅以全球的油田有限,致使能源商品价格易受政治因素、季节性以及市场供需状况的影响,再加上能源期货的全球总交易量在2006年是大幅上涨的,显示能源期货交易在全球期货交易市场中亦扮演着重要的角色,尤其机构投资人为能源期货交易中最主要的参与者,因此,了解能源价格变动所产生的风险进而利用期货或是其他衍生性商品避险的需求便应运而生。

  在早期的文献中多利用传统Naïve模型或OLS模型估算现货与期货间的避险比率,但此避险比率通常为一固定常数,对常有新资讯进入市场造成能源价格产生波动时,无法达到有效的避险,因此,在计算避险比率时,应确实考量市场状况,所以,避险比率应随时间改变而非固定不变,在本研究中就利用Bollerslev(1990)提出CCC模型与Engle(2002)提出的DCC模型搭配Bollerslev(1986)的GARCH模型与Chou(2005)提出的CARR模型估算轻甜原油期货、热燃油期货与天然气期货的动态最适避险比率,研究资料期间为1995年1月2日至2007年3月27日的日资料,并与传统Naïve模型或OLS模型估算的避险比率进行比较。

  在样本内的实证结果中,轻甜原油期货以CCC-GARCH模型、热燃油以OLS模型以及天然气以CCC-CARR模型为较佳的避险模型,但在样本外的实证结果中,三种能源资产都是采用CCC-GARCH或DCC-GARCH模型有最佳的避险绩效,显见现货与期货间的避险比率并非为一固定常数,而是会随着时间改变(time varying)的,另外,造成三种能源商品的样本内外实证结果不同原因包括CARR模型无法完全配适样本资料,以致于以报酬为基础(return-based)的模型优于以变幅为基础(range-based)的模型,再加上样本期间皆存在结构转变的现象,因而造成动态避险模型优于OLS模型。
  Crude oil keeps country’s economy running, and crude oil futures is one of the most actively traded commodity, as well as the world's largest-volume futures contract trading on a physical commodity. Energy price is highly dependent on global macroeconomic conditions, and what amount of energy futures contracts should be purchased to minimise the risk of holding spot energy is important issue in recent years.

  This research applies various methods in minimum-variance hedge strategy, and computes the Optimal Hedge Ratios (OHRs) between the amount of spot and futures for energy commodity prices using different econometric methods. Namely, using Dynamic Conditional Correlation, and DCC-CARR model proposed by Chou et. al. (2005) to compute OHRs. Other methods used for comparison include the ordinary least squares (OLS) estimator, Constant Correlation models and so on.

  The research period is from 1995 to 2007, and daily data is collected. Different methods are compared with each other in their hedging performance of variance-reduction. For the out of sample hedge, the CCC or DCC model is the best one for three commodities, and could to find the minimum-variance of a portfolio for investor. In conclusion, dynamic hedging model is better than the traditional OLS model. Meanwhile, the optimal hedge ratio is not constant, it should be time-varying.
URI: http://140.113.39.130/cdrfb3/record/nctu/#GT009437506
http://hdl.handle.net/11536/81785
显示于类别:Thesis