考虑收益率自相关特征的存货质押动态质押率设定  

Dynamic Impawn Rate of Inventory Financing under Autocorrelative Return

作　　者：何娟[1,2] 蒋祥林[2] 朱道立[3] 王建[1] 陈磊[4] 

机构地区：[1]西南交通大学交通运输与物流学院,成都610031 [2]复旦大学金融研究院,上海200433 [3]同济大学经济管理学院,上海200092 [4]华夏银行成都地区信用风险管理部,成都610041

出　　处：《管理科学》2012年第3期91-101,共11页Journal of Management Science

基　　金：国家自然科学基金(71003082);全国博士后基金(20080430602);教育部博士点基金(200806131007);中央高校基本科研业务费专项资金科技创新项目(SWJTU11CX081);四川科技计划软科学项目(2010ZR0028);复旦大学经济学院985平台项目~~

摘　　要：异于收益率弱相关的有效金融市场假说,以现货交易为主的质物市场收益率往往存在显著的自相关。从金融时间序列一般规律出发,分析质物市场收益率序列统计特征,以场外现货交易为主的螺纹钢日数据为例,模型化收益率序列自相关性和异方差性特性,建立尖峰厚尾分布下的AR(1)-GARCH(1,1)-GED模型;提出置于多风险窗口下度量未来质押期内钢材价格风险水平,给出同时考虑收益率自相关性和波动率时变性的长期风险VaR计算解析式,得出与银行风险承受能力相一致的质押率;基于失效率法则建立长期风险的碰撞序列函数,回测多风险窗口下长期VaR值。实证分析和回测显示,与现有其他模型相比,引进系数K值后的模型能显著提高银行风险覆盖率,且能显著降低银行效率损失,为银行提供一种动态质押率风险管理框架,模型确定的多风险窗口质押率与未来螺纹钢最低价值呈显著正相关。Based on efficient markets hypothesis, the return is hypothetically independent, while in a pledged inventory market where spot transactions predominate, the return is autocorrelative. In this paper, using the database of spot steel, usually traded in the OTC （over-the-counter markets）, we establish a model with the formula AR（ 1 ）-GARCH（ 1,1 ）-GED, which can better depict the feature of the autocorrelation, heteroskedasticity, leptokurtosis and fat-tails of the returns, forecasting the VaR of steel during the different risk windows in the impawn period through a method of out-of-sample, and got the impawn rate according with the risk exposure of banks. Furthermore, the hit function is established to back test the long-term price risk. The results of our experiment indicate that the introduction of coefficient K into the model can significantly improve bank risk coverage and reduce its efficiency loss. Besides, the impawn rate obtained by the model correlates positively with the lowest price in the future risk win- dows. This paper puts forward a dynamic impawn rate mode and framework for banks. The impawn rate during the different risk windows confirmed by the model is significant and positive related to the lowest value of future steel rebar.

关 键 词：AR(1)-GARCH(1 1)-GED 长期风险VaR预测 动态质押率 模型评价 

分 类 号：F830.56[经济管理—金融学]