NetworkChange1.0.0 package

Bayesian Package for Network Changepoint Analysis

BreakDiagnostic

Detect a break number using different metrics

BreakPointLoss

Compute the Average Loss of Hidden State Changes from Expected Break P...

combineVm

Combine regime-specific V matrices efficiently

drawPostAnalysis

Plot of latent node cluster

drawRegimeRaw

Plot of network by hidden regime

kmeansU

K-mean clustering of latent node positions

MakeBlockNetworkChange

Build a synthetic block-structured temporal data with breaks

MarginalCompare

Compare Log Marginal Likelihood

multiplot

Printing multiple ggplots in one file (DEPRECATED)

NetworkChange

Changepoint analysis of a degree-corrected multilinear tensor model

NetworkChangeRobust

Changepoint analysis of a degree-corrected multilinear tensor model wi...

NetworkStatic

Degree-corrected multilinear tensor model

plotContour

Contour plot of latent node positions

plotnetarray

Plot of network array data

plotU

Plot of latent node positions

plotV

Plot of layer-specific network generation rules.

scale_color_networkchange_c

NetworkChange Continuous Color Scale

scale_color_networkchange

NetworkChange Discrete Color Scale

scale_fill_networkchange

NetworkChange Discrete Fill Scale

startS

Sample a starting value of hidden states

startUV

Starting values of U and V

theme_networkchange

NetworkChange ggplot2 Theme

ULUstateSample.mpfr

Hidden State Sampler with precision

ULUstateSample

Hidden State Sampler

updateb

Update time-constant regression parameters

updatebm

Update regime-changing regression parameters

updateP

Update transition matrix

updateS

Update latent states

updates2m

Update regime-specific variance

updateU

Update time-constant latent node positions

updateUm

Regime-specific latent node positions

updateV

Update layer specific network generation rules

updateVm

Update V from a change-point network process

WaicCompare

Compare WAIC

Network changepoint analysis for undirected network data. The package implements a hidden Markov network change point model (Park and Sohn (2020)). Functions for break number detection using the approximate marginal likelihood and WAIC are also provided. This version includes performance optimizations with vectorized MCMC operations and modern ggplot2-based visualizations with colorblind-friendly palettes.

  • Maintainer: Jong Hee Park
  • License: GPL-3
  • Last published: 2026-01-21