On smooth change-point location estimation for Poisson processes

DOI10.1007/S11203-021-09240-WMaRDI QIDQ2243552zbMATH OpenOpenAlexFDO

Authors Arij Amiri, S. Dachian

Publication date 11 November 2021

Published in Statistical Inference for Stochastic Processes (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2009.13968

zbMATH Keywords

asymptotic efficiencyinhomogeneous Poisson processmaximum likelihood estimatorlocal asymptotic normalityBayesian estimatorssmooth change-point

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Bayesian inference (62F15) Markov processes: estimation; hidden Markov models (62M05) Point processes (e.g., Poisson, Cox, Hawkes processes) (60G55) Functional data analysis (62R10)

Abstract: We are interested in estimating the location of what we call "smooth change-point" from $n$ independent observations of an inhomogeneous Poisson process. The smooth change-point is a transition of the intensity function of the process from one level to another which happens smoothly, but over such a small interval, that its length $delt{a}_n$ is considered to be decreasing to $0$ as $no+infty$. We show that if $delt{a}_n$ goes to zero slower than $1/n$, our model is locally asymptotically normal (with a rather unusual rate $sqrtdelt{a}_n/n$), and the maximum likelihood and Bayesian estimators are consistent, asymptotically normal and asymptotically efficient. If, on the contrary, $delt{a}_n$ goes to zero faster than $1/n$, our model is non-regular and behaves like a change-point model. More precisely, in this case we show that the Bayesian estimators are consistent, converge at rate $1/n$, have non-Gaussian limit distributions and are asymptotically efficient. All these results are obtained using the likelihood ratio analysis method of Ibragimov and Khasminskii, which equally yields the convergence of polynomial moments of the considered estimators. However, in order to study the maximum likelihood estimator in the case where $delt{a}_n$ goes to zero faster than $1/n$, this method cannot be applied using the usual topologies of convergence in functional spaces. So, this study should go through the use of an alternative topology and will be considered in a future work.

Recommendations

• On multiple change-point estimation for Poisson process
• Misspecified change-point estimation problem for a Poisson process
• On a Poissonian change-point model with variable jump size
• On Bayesian estimators in misspecified change-point problems for Poisson process
• Estimation of the location of a 0-type or \(\infty \)-type singularity by Poisson observations

Cites work

• scientific article; zbMATH DE number 3642554 (Why is no real title available?)
• scientific article; zbMATH DE number 3733065 (Why is no real title available?)
• scientific article; zbMATH DE number 45793 (Why is no real title available?)
• scientific article; zbMATH DE number 50761 (Why is no real title available?)
• scientific article; zbMATH DE number 1546925 (Why is no real title available?)
• scientific article; zbMATH DE number 3239078 (Why is no real title available?)
• Estimation of cusp location by Poisson observations
• Estimation of the location of a 0-type or \(\infty \)-type singularity by Poisson observations
• On a Poissonian change-point model with variable jump size
• On hypothesis testing for Poisson processes: regular case
• On hypothesis testing for Poisson processes: singular cases
• On limiting likelihood ratio processes of some change-point type statistical models
• Point processes for reliability analysis. Shocks and repairable systems
• Poisson source localization on the plane: change-point case
• Poisson source localization on the plane: cusp case
• Poisson source localization on the plane: the smooth case
• Statistical inference for spatial Poisson processes

Cited in

(8)

• Estimation of the location of a 0-type or \(\infty \)-type singularity by Poisson observations
• On multiple change-point estimation for Poisson process
• On a Poissonian change-point model with variable jump size
• Misspecified change-point estimation problem for a Poisson process
• Filtering and change point estimation for hidden Markov-modulated Poisson processes
• On Bayesian estimators in misspecified change-point problems for Poisson process
• On Bayesian estimation in change-point problems for Poisson source localization on the plane in non standard situation
• Phase transitions in the estimation of event rate: a path integral analysis

This page was built for publication: On smooth change-point location estimation for Poisson processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2243552)