The University of Southampton
University of Southampton Institutional Repository

Input modelling for multimodal data

Input modelling for multimodal data
Input modelling for multimodal data
Multimodal data occurs frequently in discrete-event simulation input analysis, typically arising when an input sample stream comes from different sources. A finite mixture distribution is a simple input model for representing such data, but fitting a mixture distribution is not straightforward as the problem is well-known to be statistically non-standard. Even though much studied, the most common fitting approach, Bayesian reversible jump Markov Chain Monte Carlo (RJMCMC),is not very satisfactory for use in setting up input models. We describe an alternative Bayesian approach, MAPIS, which uses maximum a posteriori estimation with importance sampling, showing it overcomes the main problems encountered with RJMCMC. We demonstrate use of a publicly-available implementation of MAPIS,which we have called FineMix, applying it to practical examples coming from finance and manufacturing.
Simulation, Mixture Models, Input modelling
0160-5682
1038-1052
Cheng, Russell
a4296b4e-7693-4e5f-b3d5-27b617bb9d67
Currie, Christine
dcfd0972-1b42-4fac-8a67-0258cfdeb55a
Cheng, Russell
a4296b4e-7693-4e5f-b3d5-27b617bb9d67
Currie, Christine
dcfd0972-1b42-4fac-8a67-0258cfdeb55a

Cheng, Russell and Currie, Christine (2019) Input modelling for multimodal data. Journal of the Operational Research Society, 71 (6), 1038-1052. (doi:10.1080/01605682.2019.1609887).

Record type: Article

Abstract

Multimodal data occurs frequently in discrete-event simulation input analysis, typically arising when an input sample stream comes from different sources. A finite mixture distribution is a simple input model for representing such data, but fitting a mixture distribution is not straightforward as the problem is well-known to be statistically non-standard. Even though much studied, the most common fitting approach, Bayesian reversible jump Markov Chain Monte Carlo (RJMCMC),is not very satisfactory for use in setting up input models. We describe an alternative Bayesian approach, MAPIS, which uses maximum a posteriori estimation with importance sampling, showing it overcomes the main problems encountered with RJMCMC. We demonstrate use of a publicly-available implementation of MAPIS,which we have called FineMix, applying it to practical examples coming from finance and manufacturing.

Text
ChengandCurrieJORSResubmissiona - Accepted Manuscript
Download (2MB)

More information

Accepted/In Press date: 31 March 2019
e-pub ahead of print date: 4 June 2019
Keywords: Simulation, Mixture Models, Input modelling

Identifiers

Local EPrints ID: 430456
URI: http://eprints.soton.ac.uk/id/eprint/430456
ISSN: 0160-5682
PURE UUID: 81a6d8c8-fb93-4db3-9254-2b78dca6fbe4
ORCID for Christine Currie: ORCID iD orcid.org/0000-0002-7016-3652

Catalogue record

Date deposited: 01 May 2019 16:30
Last modified: 16 Mar 2024 07:47

Export record

Altmetrics

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×