Computational Statistics

, Volume 28, Issue 6, pp 2777–2796

Adaptive approximate Bayesian computation for complex models

  • Maxime Lenormand
  • Franck Jabot
  • Guillaume Deffuant
Original Paper

DOI: 10.1007/s00180-013-0428-3

Cite this article as:
Lenormand, M., Jabot, F. & Deffuant, G. Comput Stat (2013) 28: 2777. doi:10.1007/s00180-013-0428-3

Abstract

We propose a new approximate Bayesian computation (ABC) algorithm that aims at minimizing the number of model runs for reaching a given quality of the posterior approximation. This algorithm automatically determines its sequence of tolerance levels and makes use of an easily interpretable stopping criterion. Moreover, it avoids the problem of particle duplication found when using a MCMC kernel. When applied to a toy example and to a complex social model, our algorithm is 2–8 times faster than the three main sequential ABC algorithms currently available.

Keywords

ABCPopulation Monte CarloSequential Monte Carlo

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Maxime Lenormand
    • 1
  • Franck Jabot
    • 1
  • Guillaume Deffuant
    • 1
  1. 1.IRSTEALISCAubiereFrance