文档介绍：ic algorithms and Markov Chain Monte Carlo:
Differential Evolution Markov Chain makes Bayesian
computing easy
. ter Braak
x p
xR1
xi
xR2
April 2004
Biometris
quantitative methods in life and earth sciences
Differential Evolution Markov Chain: Easy puting, CJF ter Braak
Biometris is the integration of the Centre for Biometry of Plant Research International and the
Department of Mathematical and Statistical Methods of Wageningen University. Biometris, part
of Wageningen University and Research center (Wageningen UR), was established on 20th June
2001.
For more information please visit the website contact:
Biometris, Wageningen UR
. Box 100
6700 AC Wageningen, herlands
Phone: +31 (0)317 484085; Fax: +31 (0)317 483554; E-mail: ******@
month year
Report number 010404
Differential Evolution Markov Chain: Easy puting, CJF ter Braak
ic algorithms and Markov Chain Monte Carlo:
Differential Evolution Markov Chain makes Bayesian
computing easy.
Cajo J. F. Ter Braak
Biometris, Wageningen University and Research Centre, Wageningen, herlands
Address for correspondence: Cajo J. F. ter Braak, Biometris, Wageningen University and Research
Centre, Box 100, 6700 AC Wageningen, herlands.
E-mail: Cajo.******@
Differential Evolution (DE) is a simple ic algorithm for numerical optimization in real parameter
spaces. In a statistical context one would not just want the optimum but also its uncertainty. The uncertainty
distribution can be obtained by a Bayesian analysis (after specifying prior and likelihood) using Markov
Chain Monte Carlo (MCMC) simulation. In this paper the essential ideas of DE and MCMC are integrated
into Differential Evolution Markov Chain (DE-MC). DE-MC is a population MCMC algorithm, in which
multiple chains are run in parallel. DE-MC solves an important problem in MCMC, namely that of choosing
an appropriate scale and orientation for the jumping distribution. In DE-MC the jumps are simply