Abstract
The surrogate data method, classically used for non-linearity tests, amounts to the use ofsome constrained noise providing a reference for statistical testing. It is revisited here asa method for stationarization and this feature is put forward in the context ofnon-stationarity testing. The stationarization property of surrogates is first explored in atime–frequency perspective and used for devising a test of stationarity relative to anobservation time. Then, more general forms of surrogates are developed, directly intime–frequency or mixed domains of representation (ambiguity and time-lag domainsincluded), and it is shown how they allow for other tests of non-stationary features:detection of the existence of a transient in some noise; assessment of non-stationarycross-correlations.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have