Type: Package
Title: Congruence Class Models for Networks
Version: 0.1.4
Description: Provides an implementation of Congruence Class Models for generating networks. It facilitates sampling networks based on specific topological properties and attribute mixing patterns using a Markov Chain Monte Carlo framework. The implementation builds upon code from the 'ergm' package; see Handcock et al. (2008) <doi:10.18637/jss.v024.i01>.
License: GPL-3
Encoding: UTF-8
Imports: dplyr, ergm, ggplot2, gtools, igraph, intergraph, kableExtra, mvtnorm, network, RBesT, rlang, stats, tibble, tidyr, utils
Suggests: knitr, rmarkdown, testthat
VignetteBuilder: knitr
RoxygenNote: 7.3.2
NeedsCompilation: yes
Packaged: 2026-02-11 21:40:52 UTC; ravigoyal
Author: Ravi Goyal [aut, cre], Statnet Development Team [ctb, cph]
Maintainer: Ravi Goyal <ravi.j.goyal@gmail.com>
Repository: CRAN
Date/Publication: 2026-02-13 16:40:14 UTC

Compare MCMC Estimates with Theoretical Distributions

Description

This function compares the empirical MCMC distribution from sample_ccm with the theoretical distribution from the CCM model. It is used as a diagnostic tool to evaluate model adequacy.

Usage

CCM_theoretical_check(fit, n_sim = nrow(fit$mcmc_stats))

Arguments

fit

An object returned by ccm_sample.

n_sim

The number of samples drawn from the theoretical distribution

Value

A diagnostic plot comparing empirical and theoretical distributions.

Examples

ccm_sample <- sample_ccm(
  network_stats = list("edges"),
  prob_distr = list("poisson"),
  prob_distr_params = list(list(350)),
  population = 50 
)
ccm_sample<- CCM_theoretical_check(ccm_sample, n_sim = 1000)
plot(ccm_sample, stats = "edges", type = "hist", include_theoretical = TRUE)

Plot MCMC Trace for sample_ccm

Description

CCM_traceplot produces a trace plot of the MCMC samples from sample_ccm. This is used to diagnose convergence and mixing.

Usage

CCM_traceplot(object, stats = NULL, ...)

Arguments

object

A ccm_sample object.

stats

string. Which statistic to plot.

...

Additional arguments passed to plot().

Value

A trace plot for the selected MCMC chain.

Examples

ccm_sample <- sample_ccm(
  network_stats = list("edges"),
  prob_distr = list("poisson"),
  prob_distr_params = list(list(350)),
  population = 50 
)
CCM_traceplot(ccm_sample, stats = "edges")

Fit a Congruence Class Model (CCM)

Description

sample_ccm fits a Congruence Class Model using an MCMC framework to sample networks that match specific topological property distributions. It facilitates sampling based on specified network statistics (e.g., edges, degree distribution, mixing patterns) and their associated probability distributions.

Usage

sample_ccm(
  network_stats,
  prob_distr,
  prob_distr_params,
  population,
  sample_size = 1000L,
  burnin = 200000L,
  interval = 1000L,
  cov_pattern = NULL,
  initial_g = NULL,
  use_initial_g = FALSE,
  partial_network = as.integer(0),
  obs_nodes = NULL,
  Obs_stats = NULL,
  remove_var_last_entry = FALSE,
  stats_only = TRUE
)

Arguments

network_stats

Character vector of statistic names to be constrained (e.g., "edges", "degree", "density").

prob_distr

Character vector of probability distribution names corresponding to each statistic.

prob_distr_params

List of parameter sets for each specified distribution.

population

Integer. The number of nodes in the network.

sample_size

Integer. Number of MCMC samples to return. Default is 1000.

burnin

Integer. Number of MCMC iterations to discard before sampling begins. Default is 200,000.

interval

Integer. Thinning interval (number of iterations between samples). Default is 1000.

cov_pattern

Integer vector. Optional group labels or covariate patterns for nodes.

initial_g

An igraph object. The starting graph for the MCMC chain.

use_initial_g

Logical. If TRUE, the MCMC chain starts from initial_g.

partial_network

Integer. Reserved for future use in partial network observation.

obs_nodes

Integer vector. Reserved for future use in specifying observed nodes.

Obs_stats

Character vector of additional network statistics to monitor during sampling.

remove_var_last_entry

Logical. If TRUE, removes the variance constraint from the last entry of the distribution.

stats_only

Logical. If TRUE, only sufficient statistics are returned; otherwise, network objects are included.

Value

An object of class ccm_sample containing:

Examples

# Basic sampling of a random graph with an edge constraint
ccm_sample <- sample_ccm(
  network_stats = list("edges"),
  prob_distr = list("poisson"),
  prob_distr_params = list(list(350)),
  population = 50 
)
summary(ccm_sample)
plot(ccm_sample, stats = "edges", type = "hist")