Abstract: In this paper,a new method of detecting outlier in data is proposed.The new method is basedon the identification of ARMA model of system output.The outliers can be detected by a detection function. This method is very sensitive to outlier,so we can do some realtime corrections for Kalman filter.As an example of application,the new method ls applied to the guidance for semi-active radar homing missile. Thesimulation results prove that the outlier can be detected correctly,and the correction of Kalman filter is efficient and practical.