Loading Events
  • This event has passed.

Roberto CASARIN (University Ca'Foscari, Venice) "Bayesian Markov Switching Tensor Regression for Time-varying Networks"

March 14, 2019 @ 10:30 am - 11:30 am
Time: 10:30
Date: 14th of March 2019
Place: Room 3001
Roberto CASARIN (University Ca’Foscari, Venice) “Bayesian Markov Switching Tensor Regression for Time-varying Networks”
Abstract : We propose a new Bayesian Markov switching regression model for multi-dimensional arrays (tensors) of binary time series. We assume a zero-inflated logit dynamics with timevarying parameters and apply it to multi-layer temporal networks. The original contribution is threefold. First, in order to avoid over-fitting we propose a parsimonious parametrization of the model, based on a low-rank decomposition of the tensor of regression coefficients. Second, the parameters of the tensor model are driven by a hidden Markov chain, thus allowing for structural changes. The regimes are identified through prior constraints on the mixing probability of the zero-inflated model. Finally, we model the jointly dynamics of the network and of a set of variables of interest. We follow a Bayesian approach to inference, exploiting the Pólya-Gamma data augmentation scheme for logit models in order to provide an efficient Gibbs sampler for posterior approximation. We show the effectiveness of the sampler on simulated datasets of medium-big sizes, finally we apply the methodology to a real dataset of financial networks.
Jean-Michel ZAKOIAN (CREST )
 : ENSAE ParisTech
5, avenue Henry Le Chatelier
91120 Palaiseau
How to come?