Stochastic actor oriented model with random effects
Staff - Faculty of Informatics
Date: 14 October 2022 / 12:15 - 14:00
USI Campus EST, room D0.03, Sector D // online on MS Teams
You can join here
Giacomo Ceoldo, PhD student, Institute of Computing, USI
The stochastic actor oriented model (SAOM) is one of the most important tools for modelling social interactions and social behaviour over time. It can be used to model network effects both on exogenous covariates and endogenous network configurations, but also the co-evolution of behaviour and social interactions. However, one of the drawbacks of the model is that it assumes that all individuals have the same utility function. The SAOM is generalized to include random effects, so that the heterogeneity of individuals can be modelled more accurately. The linear utility function that models the probability of forming or removing a tie from the network is decomposed in a fixed part, that is the current utility of the SAOM, and a random part, in which the parameters are individual-specific and random. The Robbins-Monro algorithm that is commonly used in the SAOM, is extended to allow the estimation of the variance of the random parameters. It will be illustrated how for the model with random out-degree we can compute the parameter of the random components, and how to test its significance.
Biography: Giacomo is a PhD student at USI working with Ernst Wit, mainly on statistical models for random networks, but also on more general mathematical and computational aspects of statistical models. In his master he studied mathematics in Groningen, and in his bachelor he studied statistics in Padova.
Host: Igor Pivkin