Study of the Stationarity of Random Time Series Using the Principle of the Information-Divergence Minimum

Abstract

Using the theoretic-information approach and the criterion of the information-divergence minimum in the Kullback–Leibler metric, we propose a new algorithm for checking the time series for stationarity in a broad sense. We consider an example of realizing this algorithm, study its dynamic characteristics, and give recommendations on its use under conditions of small samples.