Detecting and analysing nonstationarity in a time series with nonlinear cross-predictions

Preprint
Publisher Website
Google Scholar
Abstract
We propose an informal test for stationarity in a time series which checks for the compatibility of nonlinear approximations to the dynamics made in different segments of the sequence. The segments are compared directly, rather than via statistical parameters. The approach provides detailed information about episodes with similar dynamics during the measurement period. Thus physically relevant changes in the dynamics can be followed.