Manifold valued data analysis of samples of networks, with applications in corpus linguistics

DOI10.1214/21-AOAS1480zbMATH Open1498.62351arXiv1902.08290OpenAlexW2948985192MaRDI QIDQ2135359FDOQ2135359

Authors: Katie E. Severn, Ian L. Dryden, Simon Preston 

Publication date: 6 May 2022

Published in: The Annals of Applied Statistics (Search for Journal in Brave)

Abstract: Networks arise in many applications, such as in the analysis of text documents, social interactions and brain activity. We develop a general framework for extrinsic statistical analysis of samples of networks, motivated by networks representing text documents in corpus linguistics. We identify networks with their graph Laplacian matrices, for which we define metrics, embeddings, tangent spaces, and a projection from Euclidean space to the space of graph Laplacians. This framework provides a way of computing means, performing principal component analysis and regression, and carrying out hypothesis tests, such as for testing for equality of means between two samples of networks. We apply the methodology to the set of novels by Jane Austen and Charles Dickens.

Full work available at URL: https://arxiv.org/abs/1902.08290

Recommendations

• Statistical analysis of network data. Methods and models
• Averages of unlabeled networks: geometric characterization and asymptotic behavior
• On multivariate network analysis of statistical data sets with different measures of association
• Model-free two-sample test for network-valued data
• Nonparametric statistics of dynamic networks with distinguishable nodes

zbMATH Keywords

hypothesis testregressiongraph Laplacianextrinsic meanRiemannian

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Applications of statistics (62P99) Statistics on manifolds (62R30) Linguistics (91F20)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Statistical analysis of network data. Methods and models
• Statistical shape analysis. With applications in R
• Title not available (Why is that?)
• Optimal Transport
• Title not available (Why is that?)
• Large sample theory of intrinsic and extrinsic sample means on manifolds. I
• Hypothesis testing for network data in functional neuroimaging
• Distances and inference for covariance operators
• Lagrange Multipliers and Optimality
• Geometric Representation of High Dimension, Low Sample Size Data
• Computing a nearest symmetric positive semidefinite matrix
• Large sample theory of intrinsic and extrinsic sample means on manifolds. II.
• Aspects of semidefinite programming. Interior point algorithms and selected applications
• Non-Euclidean statistics for covariance matrices, with applications to diffusion tensor imaging
• Two-sample bootstrap hypothesis tests for three-dimensional labelled landmark data
• Mean size-and-shapes and mean shapes: a geometric point of view
• Pivotal Bootstrap Methods fork-Sample Problems in Directional Statistics and Shape Analysis
• Procrustes metrics on covariance operators and optimal transportation of Gaussian processes
• Omnibus CLTs for Fréchet means and nonparametric inference on non-Euclidean spaces
• Averages of unlabeled networks: geometric characterization and asymptotic behavior

Cited In (1)

• Metric statistics: exploration and inference for random objects with distance profiles

Uses Software

• R
• Cytoscape
• shapes
• CVXR
• rosqp

This page was built for publication: Manifold valued data analysis of samples of networks, with applications in corpus linguistics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2135359)