TY - JOUR

T1 - Stratified Gaussian graphical models

AU - Nyman, H

AU - Pensar, Johan

AU - Corander, J

PY - 2017

Y1 - 2017

N2 - Gaussian graphical models represent the backbone of the statistical toolbox for analyzing continuous multivariate systems. However, due to the intrinsic properties of the multivariate normal distribution, use of this model family may hide certain forms of context-specific independence that are natural to consider from an applied perspective. Such independencies have been earlier introduced to generalize discrete graphical models and Bayesian networks into more flexible model families. Here, we adapt the idea of context-specific independence to Gaussian graphical models by introducing a stratification of the Euclidean space such that a conditional independence may hold in certain segments but be absent elsewhere. It is shown that the stratified models define a curved exponential family, which retains considerable tractability for parameter estimation and model selection.

AB - Gaussian graphical models represent the backbone of the statistical toolbox for analyzing continuous multivariate systems. However, due to the intrinsic properties of the multivariate normal distribution, use of this model family may hide certain forms of context-specific independence that are natural to consider from an applied perspective. Such independencies have been earlier introduced to generalize discrete graphical models and Bayesian networks into more flexible model families. Here, we adapt the idea of context-specific independence to Gaussian graphical models by introducing a stratification of the Euclidean space such that a conditional independence may hold in certain segments but be absent elsewhere. It is shown that the stratified models define a curved exponential family, which retains considerable tractability for parameter estimation and model selection.

KW - Context-specific independence

KW - Multivariate normal distribution

KW - Bayesian model learning

KW - Gaussian graphical model

KW - Context-specific independence

KW - Multivariate normal distribution

KW - Bayesian model learning

KW - Gaussian graphical model

KW - Context-specific independence

KW - Multivariate normal distribution

KW - Bayesian model learning

KW - Gaussian graphical model

U2 - 10.1080/03610926.2015.1105979

DO - 10.1080/03610926.2015.1105979

M3 - Artikel

SN - 0361-0926

VL - 46

SP - 5556

EP - 5578

JO - Communications in Statistics - Theory and Methods

JF - Communications in Statistics - Theory and Methods

IS - 11

ER -