Simulation-consistent Estimation of the Marginal Likelihood for Block Models
Date:
We propose a methodology for computing marginal likelihoods in block mo- dels, motivated by the study of information diffusion within social media groups in the context of climate change, with a particular focus on the analysis of a social network dataset based on the 2023 United Nations Climate Change Conference (COP28). The proposed estimator computes the marginal likelihood from Markov chain Monte Carlo (MCMC) samples and is simulation-consistent, asymptotically normal, and of finite variance. Moreover, it is invariant to label switching and can be computed efficiently, even for models with an arbitrarily large number of components. We evaluate the method through simulation studies in settings where the true marginal likelihood is available analytically. Finally, we apply the approach to the COP28 dataset and discuss the resulting insights.