Negative binomial graphical model with excess zeros

Markov random field or undirected graphical models (GM) are a popular class of GM useful in various fields because they provide an intuitive and interpretable graph expressing the complex relationship between random variables. The zero‐inflated local Poisson graphical model has been proposed as a gr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Statistical analysis and data mining Jg. 14; H. 5; S. 449 - 465
Hauptverfasser: Park, Beomjin, Choi, Hosik, Park, Changyi
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Hoboken Wiley Subscription Services, Inc., A Wiley Company 01.10.2021
Wiley Subscription Services, Inc
Schlagworte:
Algorithms
Complex variables
count data
Dispersion
Fields (mathematics)
Markov random field
Optimization
over‐dispersion
Polytopes
Random variables
undirected graphical model
zero inflation
ISSN:1932-1864, 1932-1872
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Markov random field or undirected graphical models (GM) are a popular class of GM useful in various fields because they provide an intuitive and interpretable graph expressing the complex relationship between random variables. The zero‐inflated local Poisson graphical model has been proposed as a graphical model for count data with excess zeros. However, as count data are often characterized by over‐dispersion, the local Poisson graphical model may suffer from a poor fit to data. In this paper, we propose a zero‐inflated local negative binomial (NB) graphical model. Due to the dependencies of parameters in our models, a direct optimization of the objective function is difficult. Instead, we devise expectation‐minimization algorithms based on two different parametrizations for the NB distribution. Through a simulation study, we illustrate the effectiveness of our method for learning network structure from over‐dispersed count data with excess zeros. We further apply our method to real data to estimate its network structure.
Bibliographie:Funding information
University of Seoul, 2018 Research Fund
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1932-1864
1932-1872
DOI:10.1002/sam.11536