Skip to Main content Skip to Navigation
Conference papers

Multivariate time-scale bootstrap for testing the equality of selfsimilarity parameters

Abstract : Monitoring one system from multivariate data collected on multiple sensors often entails counting how many actually different selfsimilarity parameters drive their temporal dynamics. Making use of a multivariate fractional Brownian motion model, of multivariate eigen-wavelet estimations, and of a multivariate time-scale block bootstrap procedure, a test for equality between pairs of sorted estimated selfsimilarity parameters is devised. The procedure permits the estimation of the test p-value and power from a single finite-size data observation. Test performance are quantified from large size Monte Carlo simulations performed under several scenarios.
Document type :
Conference papers
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03735529
Contributor : Herwig Wendt Connect in order to contact the contributor
Submitted on : Thursday, July 21, 2022 - 2:31:13 PM
Last modification on : Tuesday, August 23, 2022 - 3:45:39 PM

File

22Gretsi_ofbm_v4.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03735529, version 1

Citation

Charles-Gérard Lucas, Herwig Wendt, Patrice Abry, Gustavo Didier. Multivariate time-scale bootstrap for testing the equality of selfsimilarity parameters. XXVIIIème Colloque Francophone de Traitement du Signal et des Images (GRETSI 2022), Sep 2022, Nancy, France. ⟨hal-03735529⟩

Share

Metrics

Record views

28

Files downloads

7