The M/G/∞ estimation problem revisited

Alexander Goldenshluger

doi:10.3150/17-BEJ936

The M/G/∞ estimation problem revisited

Alexander Goldenshluger

Department of Statistics

Research output: Contribution to journal › Article › peer-review

Abstract

The subject of this paper is the M/G/∞ estimation problem: the goal is to estimate the service time distribution G of the M/G/∞ queue from the arrival–departure observations without identification of customers. We develop estimators of G and derive exact non-asymptotic expressions for their mean squared errors. The problem of estimating the service time expectation is addressed as well. We present some numerical results on comparison of different estimators of the service time distribution.

Original language	English
Pages (from-to)	2429-2460
Number of pages	32
Journal	Bernoulli
Volume	24
Issue number	4A
DOIs	https://doi.org/10.3150/17-BEJ936
State	Published - Nov 2018

Bibliographical note

Publisher Copyright:
© 2018 ISI/BS.

Keywords

M/G/∞ queue
Nonparametric estimation
Poisson point process
Rates of convergence

ASJC Scopus subject areas

Statistics and Probability

Access to Document

10.3150/17-BEJ936

Cite this

@article{6006badf290548c0b3875cce937f0aba,

title = "The M/G/∞ estimation problem revisited",

abstract = "The subject of this paper is the M/G/∞ estimation problem: the goal is to estimate the service time distribution G of the M/G/∞ queue from the arrival–departure observations without identification of customers. We develop estimators of G and derive exact non-asymptotic expressions for their mean squared errors. The problem of estimating the service time expectation is addressed as well. We present some numerical results on comparison of different estimators of the service time distribution.",

keywords = "M/G/∞ queue, Nonparametric estimation, Poisson point process, Rates of convergence",

author = "Alexander Goldenshluger",

note = "Publisher Copyright: {\textcopyright} 2018 ISI/BS.",

year = "2018",

month = nov,

doi = "10.3150/17-BEJ936",

language = "English",

volume = "24",

pages = "2429--2460",

journal = "Bernoulli",

issn = "1350-7265",

publisher = "International Statistical Institute",

number = "4A",

}

TY - JOUR

T1 - The M/G/∞ estimation problem revisited

AU - Goldenshluger, Alexander

PY - 2018/11

Y1 - 2018/11

N2 - The subject of this paper is the M/G/∞ estimation problem: the goal is to estimate the service time distribution G of the M/G/∞ queue from the arrival–departure observations without identification of customers. We develop estimators of G and derive exact non-asymptotic expressions for their mean squared errors. The problem of estimating the service time expectation is addressed as well. We present some numerical results on comparison of different estimators of the service time distribution.

AB - The subject of this paper is the M/G/∞ estimation problem: the goal is to estimate the service time distribution G of the M/G/∞ queue from the arrival–departure observations without identification of customers. We develop estimators of G and derive exact non-asymptotic expressions for their mean squared errors. The problem of estimating the service time expectation is addressed as well. We present some numerical results on comparison of different estimators of the service time distribution.

KW - M/G/∞ queue

KW - Nonparametric estimation

KW - Poisson point process

KW - Rates of convergence

UR - http://www.scopus.com/inward/record.url?scp=85045953271&partnerID=8YFLogxK

U2 - 10.3150/17-BEJ936

DO - 10.3150/17-BEJ936

M3 - Article

AN - SCOPUS:85045953271

SN - 1350-7265

VL - 24

SP - 2429

EP - 2460

JO - Bernoulli

JF - Bernoulli

IS - 4A

ER -

The M/G/∞ estimation problem revisited

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this