Genet. Sel. Evol.
Volume 33, Number 4, July-August 2001
|Page(s)||443 - 452|
Genet. Sel. Evol. 33 (2001) 443-452
Alternative implementations of Monte Carlo EM algorithms for likelihood inferencesLouis Alberto García-Cortésa and Daniel Sorensenb
a Departamento de Genética, Universidad de Zaragoza, Calle Miguel Servet 177, Zaragoza, 50013, Spain
b Section of Biometrical Genetics, Department of Animal Breeding and Genetics, Danish Institute of Agricultural Sciences, PB 50, 8830 Tjele, Denmark
(Received 14 September 2000; accepted 23 April 2001)
Two methods of computing Monte Carlo estimators of variance components using restricted maximum likelihood via the expectation-maximisation algorithm are reviewed. A third approach is suggested and the performance of the methods is compared using simulated data.
Key words: restricted maximum likelihood / Markov chain Monte Carlo / EM algorithm / Monte Carlo variance / variance components
Correspondence and reprints: Daniel Sorensen
© INRA, EDP Sciences 2001