长记忆过程参数的小波包极大似然估计方法

The Wavelet Packet Maximum Likelihood Estimation Method of Long Memory Process Parameters

基于小波包变换的解相关属性,对传统方法进行了改进,提出并推证了一种小波包极大似然估计(WPMLE)方法,并将它应用到一类有非常广泛应用背景的长记忆过程中去.仿真结果表明,在一定的精确度要求下,这种近似算法极大地降低了参数估计的计算量,可以作为参数估计方法的一种很好的选择.

Utilizing the decorrelation property of Discrete Wavelet Packet Transform （DWPT） to improve the traditional maximum likelihood estimation , this paper presents the Discrete Wavelet Packet Maximum Likelihood Estimation （DWPMLE）, and applies it into a kind of long memory processes with widely research background. Simulation results show that under certain precision demand, this improved approximate algorithm decreases the burden of computations greatly and can be used as an alternative of parameter estimation.