June 2014 Markov chain Monte Carlo for computing rare-event probabilities for a heavy-tailed random walk
Thorbjörn Gudmundsson, Henrik Hult
Author Affiliations +
J. Appl. Probab. 51(2): 359-376 (June 2014). DOI: 10.1239/jap/1402578630

Abstract

In this paper a method based on a Markov chain Monte Carlo (MCMC) algorithm is proposed to compute the probability of a rare event. The conditional distribution of the underlying process given that the rare event occurs has the probability of the rare event as its normalizing constant. Using the MCMC methodology, a Markov chain is simulated, with the aforementioned conditional distribution as its invariant distribution, and information about the normalizing constant is extracted from its trajectory. The algorithm is described in full generality and applied to the problem of computing the probability that a heavy-tailed random walk exceeds a high threshold. An unbiased estimator of the reciprocal probability is constructed whose normalized variance vanishes asymptotically. The algorithm is extended to random sums and its performance is illustrated numerically and compared to existing importance sampling algorithms.

Citation

Download Citation

Thorbjörn Gudmundsson. Henrik Hult. "Markov chain Monte Carlo for computing rare-event probabilities for a heavy-tailed random walk." J. Appl. Probab. 51 (2) 359 - 376, June 2014. https://doi.org/10.1239/jap/1402578630

Information

Published: June 2014
First available in Project Euclid: 12 June 2014

zbMATH: 1291.65014
MathSciNet: MR3217772
Digital Object Identifier: 10.1239/jap/1402578630

Subjects:
Primary: 60J22 , 65C05
Secondary: 60G50

Keywords: heavy tail , Markov chain Monte Carlo , Random walk , rare-event simulation

Rights: Copyright © 2014 Applied Probability Trust

JOURNAL ARTICLE
18 PAGES

This article is only available to subscribers.
It is not available for individual sale.
+ SAVE TO MY LIBRARY

Vol.51 • No. 2 • June 2014
Back to Top