论文部分内容阅读
本文针对已有相关文献的研究特点及不足，对我国沪深300 股指期货市场的风险测度进行了比较研究，基于其收益率的分布特征，用参数方法和非参数方法对不同分布下沪深300 股指期货的在险价值VaR 和期望损失ES 值进行了计算。
我国沪深300股指期货市场的风险测度比较研究
【摘 要】
：
本文针对已有相关文献的研究特点及不足，对我国沪深300 股指期货市场的风险测度进行了比较研究，基于其收益率的分布特征，用参数方法和非参数方法对不同分布下沪深300 股指期货的在险价值VaR 和期望损失ES 值进行了计算。
【机 构】
：
浙江大学(玉泉校区)数学系
【出 处】
：
中国现场统计研究会
【发表日期】
：
2015年3期
其他文献
Distortion risk measures are extensively used in finance and insurance applications because of their appealing properties.We present three methods to construct new class of distortion functions and me
Study of Financial Efficiency and Rate of Return of Shanghai Securities of Selection of Variables in
The paper will combine theoretical research work in mathematics and actual needs in finance,and systematically study various estimation methods in semi-parametric model and its application in financia
This paper investigates a spectrally negative Lévy risk model with regulation imposed by a regulatory authority,who exercises a regulation barrier and penalties with cost.
A test for ordered categorical variables is of considerable importance,because they are frequently encountered in biomedical studies.
会议
本文从有偏估计角度出发，提出新滤波方法——有偏自适应EKF算法，并给出了相应参数的确定方法，它可以有效地克服观测模型病态性的影响。然后在均方误差意义下对新算法的性质进行分析，研究发现在均方误差意义下，有偏自适应EKF算法优于标准EKF算法。
很多系统会同时受到退化和随机冲击的影响，而且它们存在着双向的相依关系，因此，系统的失效可以看作软失效和硬失效的竞争性失效。当系统的总退化量超过某个失效阈值时，就会引发软失效，其中总退化量包括连续的退化过程以及由随机冲击引起的突变退化量；硬失效则是由于冲击强度(极值冲击模型)或者冲击造成的累积损伤(累积冲击模型)超过了强度阈值，而该阈值受到系统退化程度的影响。
In recent years,there has been growing interest in truncation because it is a general important property in real life problems in many fields.
会议
In multivariate statistical process control(MSPC)applications,process mean shifts often occur in only a few of components.
In this paper,we consider a new estimator for determining the number of factors in factor modeling for high-dimensional stationary time series.
A test statistic based on an empirical likelihood,proposed for autoregressive models with the variance of errors scaled by an unknown nonparametric time-varying function,is stable that means not to be