Statistical Test for Dynamical Nonstationarity in Observed Time-Series Data
chao-dyn
2008-02-03 v1 Chaotic Dynamics
Abstract
Information in the time distribution of points in a state space reconstructed from observed data yields a test for ``nonstationarity''. Framed in terms of a statistical hypothesis test, this numerical algorithm can discern whether some underlying slow changes in parameters have taken place. The method examines a fundamental object in nonlinear dynamics, the geometry of orbits in state space, with corrections to overcome difficulties in real dynamical data which cause naive statistics to fail.
Cite
@article{arxiv.chao-dyn/9512005,
title = {Statistical Test for Dynamical Nonstationarity in Observed Time-Series Data},
author = {Matthew B. Kennel},
journal= {arXiv preprint arXiv:chao-dyn/9512005},
year = {2008}
}
Comments
REVTEX, 4 encapsulated postscript figures, in uuencoded, gzipped tar archive; email: kennel@msr.epm.ornl.gov