Asymptotics of trimmed CUSUM statistics

DOI10.3150/10-BEJ318zbMATH Open1229.62017OpenAlexW3105542117MaRDI QIDQ654411FDOQ654411

Authors: István Berkes, Lajos Horváth, Johannes Schauer 

Publication date: 28 December 2011

Published in: Bernoulli (Search for Journal in Brave)

Abstract: There is a wide literature on change point tests, but the case of variables with infinite variances is essentially unexplored. In this paper we address this problem by studying the asymptotic behavior of trimmed CUSUM statistics. We show that in a location model with i.i.d. errors in the domain of attraction of a stable law of parameter $0<alpha<2$, the appropriately trimmed CUSUM process converges weakly to a Brownian bridge. Thus, after moderate trimming, the classical method for detecting change points remains valid also for populations with infinite variance. We note that according to the classical theory, the partial sums of trimmed variables are generally not asymptotically normal and using random centering in the test statistics is crucial in the infinite variance case. We also show that the partial sums of truncated and trimmed random variables have different asymptotic behavior. Finally, we discuss resampling procedures which enable one to determine critical values in the case of small and moderate sample sizes.

Full work available at URL: https://arxiv.org/abs/1201.1124

Recommendations

• Asymptotic behavior of trimmed sums
• Trimmed stable AR(1) processes
• Change Point Detection with Stable AR(1) Errors
• The central limit theorem for sums of trimmed variables with heavy tails
• Asymptotic properties for the sequential CUSUM procedure

zbMATH Keywords

trimmingchange pointresamplingweak convergencestable distributions

Mathematics Subject Classification ID

Infinitely divisible distributions; stable distributions (60E07) Nonparametric hypothesis testing (62G10) Asymptotic properties of parametric tests (62F05)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• A probabilistic approach to the asymptotic distribution of sums of independent, identically distributed random variables
• Asymptotic normality and subsequential limits of trimmed sums
• Asymptotic normality of lightly trimmed means – a converse
• Asymptotic properties of the bootstrap for heavy-tailed distributions
• Bootstrap of the mean in the infinite variance case
• Laws of the iterated logarithm for sums of the middle portion of the sample
• Limit theorems for point processes and their functionals
• Limit theorems for sampling from finite populations
• Non-central limit theorems for random selections
• On Consistent Estimates of the Spectrum of a Stationary Time Series
• On the limit distributions of lightly trimmed sums
• PERIODOGRAM ANALYSIS AND CONTINUOUS SPECTRA
• Relative stability of trimmed sums
• Selection from a stable box
• Stability for sums of i.i.d. random variables when extreme terms are excluded
• Testing for changes in multivariate dependent observations with an application to temperature changes
• Testing for changes in the mean or variance of a stochastic process under weak invariance
• The asymptotic distribution of trimmed sums
• The central limit problem for trimmed sums
• The strong law of large numbers when extreme terms are excluded from sums
• What portion of the sample makes a partial sum asymptotically stable or normal?

Cited In (8)

• Trimmed stable AR(1) processes
• The central limit theorem for sums of trimmed variables with heavy tails
• Selection from a stable box
• On the central limit theorem for modulus trimmed sums
• Asymptotics for multivariate trimming
• Asymptotic behavior of trimmed sums
• Invariance principles for some FARIMA and nonstationary linear processes in the domain of a stable distribution
• Rejoinder on: ``Extensions of some classical methods in change point analysis

This page was built for publication: Asymptotics of trimmed CUSUM statistics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q654411)