吉林大学学报(理学版)

• 数学 • 上一篇    下一篇

一类非线性随机微分方程的参数估计

王素丽, 吕艳   

  1. 南京理工大学 理学院, 南京 210094
  • 收稿日期:2016-05-06 出版日期:2017-03-26 发布日期:2017-03-24
  • 通讯作者: 吕艳 E-mail:lvyan1998@aliyun.com

Parameter Estimation of a Class of NonlinearStochastic Differential Equations

WANG Suli, LV Yan   

  1. School of Science, Nanjing University of Science and Technology, Nanjing 210094, China
  • Received:2016-05-06 Online:2017-03-26 Published:2017-03-24
  • Contact: LV Yan E-mail:lvyan1998@aliyun.com

摘要: 利用极大似然估计方法, 考虑一类具有小扰动的非线性随机微分方程的参数估计问题. 讨论小扰动项ε→0或时间T→∞时估计量的性质, 证明了: 当ε→0时, 未知参数的估计量具有无偏性及渐近一致性; 当ε取固定值和ε→0时, 分别给出了估计量α^ε在T→∞时的渐近分布. 最后给出数值模拟结果, 验证了估计量的无偏性及其渐近正态性.

关键词: 渐近正态性, 非线性随机微分方程, 无偏性, 参数估计

Abstract: By using the maximum likelihood estimation (MLE) method , we considered the parameter estimation problem of a class of nonlinear stochas tic differential equations with small perturbation. We discussed the properties of the esitmator as the small perturbation parameter ε→0 or ti me T→∞, and proved that the estimator of unknown parameter had unbiasedness and asymptotic consistency as ε→0. When ε took a fix ed value and ε→0, we gave the asymptotic distribut ion of the estimator α^ε as T→∞ respectively. Finallay, we gave the numerical simulation results to veri fy the unbiasedness and asymptotic normality of estimator.

Key words: parameter estimation, asymptotic normality, unbiasedness, nonlinear stochastic differential equation

中图分类号: 

  • O211.63