Detecting differences between delay vector distributions
- 1 March 1996
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review E
- Vol. 53 (3) , 2169-2176
- https://doi.org/10.1103/physreve.53.2169
Abstract
We propose a test for the null hypothesis that two sets of vectors are drawn from the same multidimensional probability distribution. The application to delay vector distributions provides a test for the null hypothesis that two time series have been generated by the same mechanism. © 1996 The American Physical Society.Keywords
This publication has 10 references indexed in Scilit:
- Reversibility as a criterion for discriminating time seriesPhysics Letters A, 1995
- Two-Sample Test Statistics for Measuring Discrepancies Between Two Multivariate Probability Density Functions Using Kernel-Based Density EstimatesJournal of Multivariate Analysis, 1994
- Quantifying the closeness of fractal measuresPhysical Review E, 1994
- The Three Sigma RuleThe American Statistician, 1994
- Recognition and classification of nonlinear chaotic signalsChaos: An Interdisciplinary Journal of Nonlinear Science, 1993
- NONLINEAR TIME SEQUENCE ANALYSISInternational Journal of Bifurcation and Chaos, 1991
- Statistical precision of dimension estimatorsPhysical Review A, 1990
- Spurious dimension from correlation algorithms applied to limited time-series dataPhysical Review A, 1986
- Independent coordinates for strange attractors from mutual informationPhysical Review A, 1986
- A Berry-Esseen bound for symmetric statisticsProbability Theory and Related Fields, 1984