Home // SIMUL 2015, The Seventh International Conference on Advances in System Simulation // View article

Statistical Emulation Applied to a Very Large Data Set Generated by an Agent-based Model

Authors:
Wim De Mulder
Bernhard Rengs
Geert Molenberghs
Thomas Fent
Geert Verbeke

Keywords: Statistical emulation; Agent-based models; Cluster analysis; Genetic algorithms

Abstract:
This paper presents a method to apply statistical emulation on very large data sets, making use of cluster analysis. It is shown how integrating cluster analysis with the interpolation method called inverse distance weighting, naturally generalizes the basic emulation framework where a single Gaussian distribution is used, to a framework where a mixture of Gaussians is employed. Our results indicate that it might be advantageous to choose a different number of Gaussians in the mixture depending on the goal of the subsequent analysis. For example, is a certain estimation needed or is a confidence interval required? Some interesting future research questions are discussed. Our work is truly interdisciplinary, covering the fields of statistical emulation, demography, agent-based models, genetic algorithms and cluster analysis.

Pages: 43 to 48

Copyright: Copyright (c) IARIA, 2015

Publication date: November 15, 2015

Published in: conference

ISSN: 2308-4537

ISBN: 978-1-61208-442-8

Location: Barcelona, Spain

Dates: from November 15, 2015 to November 20, 2015