arrow
Search icon

Latent variable modelling of interdependent ego-networks.

MACSI at the  department of Mathematics and Statistics at the University of Limerick invites you to a seminar

Speaker:                     Dr. Isabella Gollini (School of Mathematics and Statistics, University College Dublin).

Time and location:    Friday 28th September, at 4 p.m. in Room A2-002

Title:                           Latent variable modelling of interdependent ego-networks.

Abstract: Ego-networks consist of a focal node ("ego") and the nodes to whom ego is directly connected to ("alters"). Often network data are collected as interdependent ego-networks (a network of ego-networks) and they require ad hoc modelling approaches to explain the complexity of their data structure.
We present a Bayesian latent variable network modelling framework to describe the connectivity structure of interdependent ego-networks. This allows us to explain both the ego-ego and ego-alter relational structures simultaneously by estimating the positions of all the individuals in a latent "social space". The challenge concerning this model is represented by the intractability of the likelihood; to efficiently overcome this difficulty we adopt an efficient variational algorithm. The flexible modelling framework presented together with a fast inferential approach can be adapted to a wide range of network settings.
In this work, we illustrate this new methodology by exploring the structure of human smuggling network out of Libya consisting of ego-networks based on the wiretaps acquired by the Italian police on 29 suspects during an investigation period lasting from January to October 2014. The statistical challenge with these ego-networks is that the large number of alters (more than 15k) can potentially be members of several ego-networks.
The analysis is carried out using the lvm4net package for R that is available on CRAN.

If you have any questions regarding this seminar, please direct them to Romina Gaburro (061 2131930, email romina.gaburro@ul.ie  and Clifford Nolan (061 202766), clifford.nolan@ul.ie).

Supported by Science Foundation Ireland funding, MACSI - the Mathematics Applications Consortium for Science and Industry (www.macsi.ul.ie), centred at the University of Limerick, is dedicated to the mathematical modelling and solution of problems which arise in science, engineering and industry in Ireland.

Sfi logo