A criterion for hypothesis testing for stationary processes - Archive ouverte HAL Access content directly
Reports (Research Report) Year : 2009

A criterion for hypothesis testing for stationary processes

(1, 2)
1
2

Abstract

Given a finite-valued sample $X_1,\dots,X_n$ we wish to test whether it was generated by a stationary ergodic process belonging to a family $H_0$, or it was generated by a stationary ergodic process outside $H_0$. We require the Type I error of the test to be uniformly bounded, while the type II error has to be mande not more than a finite number of times with probability 1. For this notion of consistency we provide necessary and sufficient conditions on the family $H_0$ for the existence of a consistent test. This criterion is illustrated with applications to testing for a membership to parametric families, generalizing some existing results. In addition, we analyze a stronger notion of consistency, which requires finite-sample guarantees on error of both types, and provide some necessary and some sufficient conditions for the existence of a consistent test. We emphasize that no assumption on the process distributions are made beyond stationarity and ergodicity.
Fichier principal
Vignette du fichier
1cf.pdf (152.6 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00389689 , version 1 (29-05-2009)
inria-00389689 , version 2 (30-05-2009)
inria-00389689 , version 3 (19-10-2009)
inria-00389689 , version 4 (26-12-2014)

Identifiers

  • HAL Id : inria-00389689 , version 4
  • ARXIV : 0905.4937

Cite

Daniil Ryabko. A criterion for hypothesis testing for stationary processes. [Research Report] INRIA Lille. 2009. ⟨inria-00389689v4⟩
271 View
187 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More