A network Poisson model for weighted directed networks with covariates

DOI10.1080/03610926.2021.2005101arXiv2107.10735OpenAlexW3215358786MaRDI QIDQ6170102FDOQ6170102

Authors: Meng Xu, Qiuping Wang 

Publication date: 12 July 2023

Published in: Communications in Statistics: Theory and Methods (Search for Journal in Brave)

Abstract: The edges in networks are not only binary, either present or absent, but also take weighted values in many scenarios (e.g., the number of emails between two users). The covariate-$p_0$ model has been proposed to model binary directed networks with the degree heterogeneity and covariates. However, it may cause information loss when it is applied in weighted networks. In this paper, we propose to use the Poisson distribution to model weighted directed networks, which admits the sparsity of networks, the degree heterogeneity and the homophily caused by covariates of nodes. We call it the emph{network Poisson model}. The model contains a density parameter $mu$, a $2n$-dimensional node parameter $heta$ and a fixed dimensional regression coefficient $gamma$ of covariates. Since the number of parameters increases with $n$, asymptotic theory is nonstandard. When the number $n$ of nodes goes to infinity, we establish the $el{l}_{i}nfty$-errors for the maximum likelihood estimators (MLEs), $hatheta$ and $hatgamma$, which are $O_p((logn/n{)}^{1/2})$ for $hatheta$ and $O_p(logn/n)$ for $hatgamma$, up to an additional factor. We also obtain the asymptotic normality of the MLE. Numerical studies and a data analysis demonstrate our theoretical findings. ) for b{ heta} and Op(log n/n) for b{gamma}, up to an additional factor. We also obtain the asymptotic normality of the MLE. Numerical studies and a data analysis demonstrate our theoretical findings.

Full work available at URL: https://arxiv.org/abs/2107.10735

zbMATH Keywords

asymptotic normalityconsistencycovariatesmaximum likelihood estimatorweighted directed networks

Mathematics Subject Classification ID

Statistics (62-XX)

Cites Work

• A survey of statistical network models
• Consistent Estimates Based on Partially Consistent Observations
• Statistical analysis of network data. Methods and models
• An Exponential Family of Probability Distributions for Directed Graphs
• Title not available (Why is that?)
• Title not available (Why is that?)
• A review of dynamic network models with latent variables
• Maximum likelihood estimation in the \(\beta\)-model
• Random graphs with a given degree sequence
• Optimal Error Bounds for the Newton–Kantorovich Theorem
• Title not available (Why is that?)
• A central limit theorem in the \(\beta \)-model for undirected random graphs with a diverging number of vertices
• Asymptotics in undirected random graph models parameterized by the strengths of vertices
• Asymptotics in directed exponential random graph models with an increasing bi-degree sequence
• An econometric model of network formation with degree heterogeneity
• Statistical inference in a directed network model with covariates
• Analysis of Networks via the Sparseβ-model
• Inference in a probit model for affiliation networks
• Asymptotics in a probit model for directed networks

Cited In (2)

• Compound Poisson models for weighted networks with applications in finance
• Monitoring social networks based on Zero-inflated Poisson regression model

This page was built for publication: A network Poisson model for weighted directed networks with covariates

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6170102)