偏最小二乘回归在美式-亚式期权定价中的应用  

Application of partial least-squares regression in valuing American-Asian option

作　　者：王旭[1] 王拉省[1] 

机构地区：[1]西安工程大学理学院,陕西西安710048

出　　处：《纺织高校基础科学学报》2008年第1期124-127,130,共5页Basic Sciences Journal of Textile Universities

基　　金：陕西省教育厅自然科学专项基金资助项目(05JK207)

摘　　要：利用蒙特卡罗模拟得到几何布朗运动环境下标的资产的价格路径样本,然后应用偏最小二乘回归给出了美式-亚式期权的价格.与基于扰动分析估计的随机近似方法及普通最小二乘回归方法相比,在保证精度的前提下,该方法具有更好的稳定性和更快的收敛速度.An American-Asian is valued option based on the partial least-squares regression. In the interim, the price samples of underlying asset in the option are obtained by using Monte Carlo simulation, whose price process obeys Geometric Brownian Motion. Compared with the stochastic approximation method based on the perturbation analysis estimators and the simple least-squares approach, this method has better stability and higher convergence speed, besides on the premise of ensuring accuracy.

关 键 词：蒙特卡罗模拟 偏最小二乘回归 关式-亚式期权 

分 类 号：F736.2[经济管理—产业经济]