stergm_MCMC_sample is a low-level internal function not intended to
be called directly by end users. It collects a sample of networks and
returns the formation and dissolution statistics of each sample, along with
a toggle matrix of the changes needed from the original network to each in
the sample.
stergm_MCMC_slave is an even
lower-level function that actually calls the C code.
stergm_MCMC_sample(nw, model.form, model.diss, model.mon, proposal.form,
proposal.diss, control, theta.form = NULL, theta.diss = NULL,
verbose = FALSE, ..., eta.form = ergm.eta(theta.form,
model.form$etamap), eta.diss = ergm.eta(theta.diss, model.diss$etamap))stergm_MCMC_slave(Clist.form, Clist.diss, Clist.mon, proposal.form,
proposal.diss, eta.form, eta.diss, control, verbose)
a network object
formation, dissolution, and
monitoring model, as returned by ergm_model
a list of parameters needed for proposals of the formations and dissolutions
list of control paramters, probably from
control.stergm
logical; whether this and other functions should be verbose
vectors of natural parameters.
formation, dissolution, and
monitoring "Clist", as returned by ergm.Cprepare
returns the MCMC sample as a list containing:
statsmatrix.form: the matrix of sampled statistics for 'model.form' RELATIVE TO INITIAL NETWORK
statsmatrix.diss: the matrix of sampled statistics for 'model.form' RELATIVE TO INITIAL NETWORK
statsmatrix.mon: the matrix of sampled statistics for 'model.mon' RELATIVE TO INITIAL NETWORK
newnetwork : the final network from the sampling process
changed : a toggle matrix, where the first column is
the timestamp of the toggle and the 2nd and 3rd columns are the head & tail
of the toggle; this is only returned if control$changes is not NULL
maxchanges : the "MCMC Dyn workspace"; see 'maxchanges' in the input param list
This function is normally called inside simulate.stergm to
prepare inputs for the C sampling code and return its results