Disorder Indicator for Nonstationary Stochastic Processes

Abstract

The properties of a statistic called a self-consistent stationary level of nonstationary time series are examined. It is shown that a change in this statistic can be treated as a disorder in the nonstationarity properties of the series. The significance level of decision making is estimated, characteristic periods in a nonstationary stochastic process are detected, and an optimal sample size for constructing indicators in stochastic control problems is determined. A disorder indicator for electroencephalogram data from epilepsy patients is studied as a practical application.