Approximate Variational Estimation for a Model of Network Formation
The Review of Economics and Statistics · 06.01.2023 · 105 (1) · 113-124
DOI: 10.1162/rest_a_01023 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Review of Economics and Statistics, online erschienen am 06.01.2023. Verfasst von Angelo Mele und 1 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 39 Literaturangaben.
Abstract (Originalsprache)
We develop approximate estimation methods for exponential random graph models (ERGMs), whose likelihood is proportional to an intractable normalizing constant. The usual approach approximates this constant with Monte Carlo simulations; however, convergence may be exponentially slow. We propose a deterministic method, based on a variational mean-field approximation of the ERGM's normalizing constant. We compute lower and upper bounds for the approximation error for any network size, adapting nonlinear large deviation results. This translates into bounds on the distance between true likelihood and mean-field likelihood. Monte Carlo simulations suggest that in practice, our deterministic method performs better than our conservative theoretical approximation bounds imply, for a large class of models.
Zitieren
APA
Mele, A., & Zhu, L. (2023). Approximate Variational Estimation for a Model of Network Formation. The Review of Economics and Statistics, 105(1), 113-124. https://doi.org/10.1162/rest_a_01023
Vancouver
Mele A, Zhu L. Approximate Variational Estimation for a Model of Network Formation. The Review of Economics and Statistics. 2023;105(1):113-124. doi:10.1162/rest_a_01023
BibTeX
@article{Mele2023,
author = {Mele, Angelo and Zhu, Lingjiong},
title = {Approximate Variational Estimation for a Model of Network Formation},
journal = {The Review of Economics and Statistics},
year = {2023},
volume = {105},
number = {1},
pages = {113--124},
doi = {10.1162/rest_a_01023}
}
EUVIMED