跳跃CKLS模型的MCMC估计与应用  

Parameter Estimation of Jump CKLS Model and Its Application

作　　者：孙琳[1] 

机构地区：[1]广东工业大学应用数学学院,广东广州510090

出　　处：《广东工业大学学报》2010年第2期68-70,76,共4页Journal of Guangdong University of Technology

摘　　要：考虑金融市场的非系统风险,在传统的CKLS模型中加入随机跳跃因素,提出了一种刻画短期利率的扩展CKLS模型.采用Euler法离散化连续过程,得到离散过程的似然函数,并采用基于马尔可夫链蒙特卡洛法估计了模型的未知参数.采用上海银行间同业拆放利率数据进行实证研究.结果表明,跳跃在所选的研究期间以较高的概率发生,马尔可夫链蒙特卡洛法在参数估计中是有效的.Regarding the non-system risks in the financial market,the extended CKLS model,which describes the short-term interest rate,was proposed,based on the traditional CKLS model.Then,the likelihood function in discrete form was obtained by using the Euler method to approximate the continuous process.Furthermore,the parameters of this model were estimated by Markov Chain Monte Carlo method.Finally,based on O/N SHIBOR,an empirical study was presented.The results indicate jumps happen with a high probability in the research time and Markov Chain Monte Carlo method is effective in parameter estimation.

关 键 词：马尔可夫链蒙特卡洛 跳跃CKLS模型 上海银行间同业拆放利率 利率模型 

分 类 号：F830[经济管理—金融学] O212[理学—概率论与数理统计]