Document ESAIM: P&S, June 2005, Vol. 9, pp. 241-253
DOI: 10.1051/ps:2005012
Estimation of parameters in a network reliability model with spatial dependence
Ian Hepburn DinwoodieISDS, Box 90251, Duke University, Durham NC 27708, USA; ihd@stat.duke.edu
(Received October 3, 2003. Revised May 10, 2005.)
Abstract
An iterative method based on a fixed-point property
is proposed for finding maximum likelihood
estimators for parameters in a model of network reliability with
spatial dependence. The method is shown to converge at a geometric rate under
natural conditions on data.
Mathematics Subject Classification. 62B05, 62F10
Key words: Curie-Weiss, EM-algorithm, iterative proportional scaling, maximum likelihood, network tomography.
© EDP Sciences, SMAI 2005