User: Guest  Login
Title:

Marginal likelihood and model selection for Gaussian latent tree and forest models

Document type:
Zeitschriftenaufsatz
Author(s):
Drton, Mathias; Lin, Shaowei; Weihs, Luca; Zwiernik, Piotr
Abstract:
Gaussian latent tree models, or more generally, Gaussian latent forest models have Fisher-information matrices that become singular along interesting submodels, namely, models that correspond to subforests. For these singularities, we compute the real log-canonical thresholds (also known as stochastic complexities or learning coefficients) that quantify the large-sample behavior of the marginal likelihood in Bayesian inference. This provides the information needed for a recently introduced gener...     »
Keywords:
algebraic statistics, Gaussian graphical model, latent tree models, marginal likelihood, multivariate normal distribution, singular learning theory
Dewey Decimal Classification:
510 Mathematik
Journal title:
Bernoulli
Year:
2017
Journal volume:
23
Year / month:
2017-02
Quarter:
1. Quartal
Month:
Feb
Journal issue:
2
Pages contribution:
1202-1232
Language:
en
Fulltext / DOI:
doi:10.3150/15-bej775
WWW:
Project Euclid
Publisher:
Bernoulli Society for Mathematical Statistics and Probability
E-ISSN:
1350-7265
Date of publication:
01.05.2017
 BibTeX