Kalman Filter and Maximum Likelihood Estimation to Asset Return
回报率的滤波与极大似然估计

It is common to take geometric Brownian motion as a model for asset prices but it is difficult to get a good estimation to the drift coefficient.Utilizing statistical filter techniques,this paper provides the Kalman filter estimation for the drift coefficient.The comparison between the Kalman filter and the maximum likelihood approach is presented.We also show an example by Monte Carlo simulation.The results explain that the Kalman filter appears much superior to the maximum likelihood estimation.