Memory-based persistence in a counting random walk process

Pierre Vallois, Charles Tapiero

Research output: Contribution to journalArticle

Abstract

This paper considers a memory-based persistent counting random walk, based on a Markov memory of the last event. This persistent model is a different than the Weiss persistent random walk model however, leading thereby to different results. We point out to some preliminary result, in particular, we provide an explicit expression for the mean and the variance, both nonlinear in time, of the underlying memory-based persistent process and discuss the usefulness to some problems in insurance, finance and risk analysis. The motivation for the paper arose from the counting of events (whether rare or not) in insurance that presume that events are time independent and therefore based on the Poisson distribution for counting these events.

Original languageEnglish (US)
Pages (from-to)303-317
Number of pages15
JournalPhysica A: Statistical Mechanics and its Applications
Volume386
Issue number1
DOIs
StatePublished - Dec 1 2007

Fingerprint

random walk
Persistence
Counting
Random walk
counting
Insurance
Rare Events
Risk Analysis
Poisson distribution
finance
Finance
Model

Keywords

  • Insurance
  • Markov chains
  • Persistence
  • Random walk

ASJC Scopus subject areas

  • Mathematical Physics
  • Statistical and Nonlinear Physics

Cite this

Memory-based persistence in a counting random walk process. / Vallois, Pierre; Tapiero, Charles.

In: Physica A: Statistical Mechanics and its Applications, Vol. 386, No. 1, 01.12.2007, p. 303-317.

Research output: Contribution to journalArticle

@article{24095bf268a4496780aa1c604c131478,
title = "Memory-based persistence in a counting random walk process",
abstract = "This paper considers a memory-based persistent counting random walk, based on a Markov memory of the last event. This persistent model is a different than the Weiss persistent random walk model however, leading thereby to different results. We point out to some preliminary result, in particular, we provide an explicit expression for the mean and the variance, both nonlinear in time, of the underlying memory-based persistent process and discuss the usefulness to some problems in insurance, finance and risk analysis. The motivation for the paper arose from the counting of events (whether rare or not) in insurance that presume that events are time independent and therefore based on the Poisson distribution for counting these events.",
keywords = "Insurance, Markov chains, Persistence, Random walk",
author = "Pierre Vallois and Charles Tapiero",
year = "2007",
month = "12",
day = "1",
doi = "10.1016/j.physa.2007.08.027",
language = "English (US)",
volume = "386",
pages = "303--317",
journal = "Physica A: Statistical Mechanics and its Applications",
issn = "0378-4371",
publisher = "Elsevier",
number = "1",

}

TY - JOUR

T1 - Memory-based persistence in a counting random walk process

AU - Vallois, Pierre

AU - Tapiero, Charles

PY - 2007/12/1

Y1 - 2007/12/1

N2 - This paper considers a memory-based persistent counting random walk, based on a Markov memory of the last event. This persistent model is a different than the Weiss persistent random walk model however, leading thereby to different results. We point out to some preliminary result, in particular, we provide an explicit expression for the mean and the variance, both nonlinear in time, of the underlying memory-based persistent process and discuss the usefulness to some problems in insurance, finance and risk analysis. The motivation for the paper arose from the counting of events (whether rare or not) in insurance that presume that events are time independent and therefore based on the Poisson distribution for counting these events.

AB - This paper considers a memory-based persistent counting random walk, based on a Markov memory of the last event. This persistent model is a different than the Weiss persistent random walk model however, leading thereby to different results. We point out to some preliminary result, in particular, we provide an explicit expression for the mean and the variance, both nonlinear in time, of the underlying memory-based persistent process and discuss the usefulness to some problems in insurance, finance and risk analysis. The motivation for the paper arose from the counting of events (whether rare or not) in insurance that presume that events are time independent and therefore based on the Poisson distribution for counting these events.

KW - Insurance

KW - Markov chains

KW - Persistence

KW - Random walk

UR - http://www.scopus.com/inward/record.url?scp=35148843789&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35148843789&partnerID=8YFLogxK

U2 - 10.1016/j.physa.2007.08.027

DO - 10.1016/j.physa.2007.08.027

M3 - Article

AN - SCOPUS:35148843789

VL - 386

SP - 303

EP - 317

JO - Physica A: Statistical Mechanics and its Applications

JF - Physica A: Statistical Mechanics and its Applications

SN - 0378-4371

IS - 1

ER -