Uncovering latent structure in valued graphs: a variational approach
Language
en
Article de revue
This item was published in
Annals of Applied Statistics. 2010, vol. 4, n° 2, p. 715-742
Institute of Mathematical Statistics
English Abstract
As more and more network-structured data sets are available, the statistical analysis of valued graphs has become common place. Looking for a latent structure is one of the many strategies used to better understand the ...Read more >
As more and more network-structured data sets are available, the statistical analysis of valued graphs has become common place. Looking for a latent structure is one of the many strategies used to better understand the behavior of a network. Several methods already exist for the binary case. We present a model-based strategy to uncover groups of nodes in valued graphs. This framework can be used for a wide span of parametric random graphs models and allows to include covariates. Variational tools allow us to achieve approximate maximum likelihood estimation of the parameters of these models. We provide a simulation study showing that our estimation method performs well over a broad range of situations. We apply this method to analyze host parasite interaction networks in forest ecosystems.Read less <
English Keywords
ECOLOGICAL NETWORKS
HOST–PARASITE INTERACTIONS
LATENT STRUCTURE
MIXTURE
MODEL
RANDOM GRAPH
VALUED GRAPH
VARIATIONAL METHOD
RELATION HOTE-PARASITE
Origin
Hal imported