gof.multibergm: Goodness-of-fit diagnostics for multibergm

In brieuclehmann/multibergm: Bayesian Exponential Random Graph Models for Multiple Networks

Goodness-of-fit diagnostics for multibergm

Description

Function to calculate summaries for degree, minimum geodesic distances, and edge-wise shared partner distributions to diagnose the Bayesian goodness-of-fit of exponential random graph models fit to multiple networks.

Usage

## S3 method for class 'multibergm'
gof(
  object,
  coefs = NULL,
  param = NULL,
  sample_size = 100L,
  aux_iters = 1.5 * object$control$aux_iters,
  burn_in = 0L,
  thin = 1L,
  ...
)

Arguments

object	A multibergm object
coefs	Optional set of model coefficients to use for network simulation. The default is to use the posterior samples of the population-level parameter.
param	Multibergm parameter to be summarised
sample_size	Number of networks to be simulated and compared to the observed networks.
aux_iters	Number of iterations used for network simulation.
burn_in	Amount of burn-in to remove from the start of posterior samples (pre-thinning)
thin	Amount of thinning to apply to the posterior samples
...	Additional parameters to be passed on to lower-level functions.

Value

Outputs bar plots (for observed networks) overlayed with ribbons (for simulated network) of degree, minimum geodesic distances, and edge-wise shared partner distributions.

brieuclehmann/multibergm documentation built on June 19, 2024, 6:36 p.m.