On computer‐intensive simulation and estimation methods for rare‐event analysis in epidemic models

Abstract

This article focuses, in the context of epidemic models, on rare events that may possibly correspond to crisis situations from the perspective of public health. In general, no close analytic form for their occurrence probabilities is available, and crude Monte Carlo procedures fail. We show how recent intensive computer simulation techniques, such as interacting branching particle methods, can be used for estimation purposes, as well as for generating model paths that correspond to realizations of such events. Applications of these simulation-based methods to several epidemic models fitted from real datasets are also considered and discussed thoroughly.

Extinction Probabilities for a Distylous Plant Population Modeled by an Inhomogeneous Random Walk on the Positive Quadrant

“…formances of the Monte-Carlo method match better the one of the deterministic algorithm. This is due to the fact that Monte-Carlo methods fail to produce good estimates of small probabilities (see [5] and references therein). When the probabilities p (3) i,j 's are given by the deterministic method with N = 50 in (4.2), we have as in the previous case (r = 3) an exponential decrease of the relative quadratic error in exp(−0.1092 N ) (R 2 = 95.07%).…”

“…formances of the Monte-Carlo method match better the one of the deterministic algorithm. This is due to the fact that Monte-Carlo methods fail to produce good estimates of small probabilities (see [5] and references therein). When the probabilities p…”

A Study on the Performance of Oracle Grid Engine for Computing Intensive Applications

“…Computing intensive applications (also known as compute intensive, computer intensive or computation intensive) are a family of applications arising in large simulations [5], [8] from many fields including bio-medicine [4] and genomics [9], finance [17], gaming, image processing [10], embedded applications, etc. that perform computationally intensive work and usually might need to run in batch mode for an extended period of time.…”