Node-specific effects in latent space modelling of multidimensional networks
share
Observed multidimensional network data can have different levels of complexity, as nodes may be characterized by heterogeneous individual-specific features. Also, such characteristics may vary across the networks. This article discusses a novel class of models for multidimensional networks, able to deal with different levels of heterogeneity within and between networks. The proposed framework is developed within the family of latent space models, in order to distinguish recurrent symmetrical relations between the nodes from node-specific features in the different views. Models parameters are estimated via a Markov Chain Monte Carlo algorithm. Simulated data and also FAO fruits import/export data are analysed to illustrate the performances of the proposed models.
READ FULL TEXT