Robust recursive time series modeling based on an AR model excited by a t-distribution process

In this correspondence, a new robust recursive spectral estimation based on an AR model is proposed. The optimal coefficients are selected by assuming that the excitation signal has a t-distribution t(α) with α degrees of freedom. With α=∞, we get the RLS method. Simulation results show that the obtained estimates using the proposed method with small α are more efficient, and the standard deviation (SD) of the estimation results is smaller and more accurate than that with large α. The proposed estimator with small α is also more efficient and more accurate than the recursive method based on Huber´s M estimate. Two approaches are used, i.e., the infinite memory and the exponentially weighted approaches