A NEW METHOD OF NONSTATIONARY TIME-SERIES ANALYSIS BASED ON INHOMOGENEOUS AR EQUATION

We propose a new model for nonstationary time series analysis. The mod el Is of a noise-contaminated signal of an AR system excited by a sequ ence of an input signal represented in terms of orthogonal functions. We also propose an algorithm that enables us to estimate parameters of the AR part and the input signal simultaneously. The models are final ly evaluated by testing the recovery of an output signal. Examples of data analysis of the synthetic time series are shown for the case in w hich the input signal is represented by a sequence of wavelets.