基于VaR的风险测度方法既侧重收益的负向波动风险,又可通过置信水平的设定满足有不同风险偏好的投资者的需求。以具有金融和商品双重属性的黄金为实证对象,充分考虑现货和期货市场的非对称性、两者之间的协整关系以及非线性相关的特征,以风险最小化为原则,建立M—Copula—GJR—VaR动态套期保值比率估计模型。采用中国市场现货价格和期货价格数据。对比分析M-Copula-GJR-VaR模型与CCC-GARCH-VaR模型、DCC—GARCH—VaR模型、Clayton Copula-GJR-VaR模型和Gumbel Copula-GJR-VaR模型的套期保值比率和套期保值效果。研究结果表明,经过4年多的发展,套期保值效率处于0.672~0.704之间的中国黄金期货市场还不成熟,套期保值功能的发挥有待提高;采用M-Copula-GJR—VaR模型估计的套期保值比率最优且套期保值效果最好,应用该模型进行黄金市场套期保值操作,可达到以相对较少的套期保值成本较大程度地规避现货市场价格风险的目的。
The VaR risk measure not only focuses on the negative fluctuation risk of yields, but also meets the needs of investors with different risk preferences by setting appropriate confidence levels. Taking gold, which owns dual properties of financial and commodity, as the empirical study object, this study takes full account of the asymmetry, the co-integration relationship and the nonlinear correlation of the spot and futures markets and builds the M-Copnla-GJR-VaR dynamic hedging ratios estimation model with the risk minimization principle. The research adopts data from spot price and futures price in Chinese market and 6ompares the hedging ratios and hedging effects of M-Copnla-GJR-VaR model with those of CCC-GARCH-VaR model, DCC-GARCH-VaR model, Clayton-Copula-GJR-VaR model and Gumbel-Copnla-GJR-VaR model. The results show that, after more than 4 years development, the hedging effects of the Chinese gold futures market are between 0.672 and 0.704, which indicates that the market is not yet mature and the hedging function still needs improvement; the hedging ratios and hedging effects of M-Copnla-GJR-VaR model beast best results, so if the model is applied to the hedging operations in gold market, the goal of circumventing the spot market price risk to a large extent with relatively few hedging costs can be achieved.