This function is a wrapper around ergm.bridge.llr that uses a
dyad-independent ERGM as a starting point for bridge sampling to
estimate the log-likelihood for a given dyad-dependent model and
parameter configuration. The dyad-independent model may be specified
or can be chosen adaptively.
ergm.bridge.dindstart.llk(object,
response=NULL,
constraints=~.,
coef,
dind=NULL,
coef.dind=NULL,
basis=NULL,
…,
llkonly=TRUE,
control=control.ergm.bridge())A model formula. See ergm for details.
The name of the edge attribute that is the response. Note that it's
included solely for consistency, since
ergm.bridge.dindstart.llk can only handle binary ERGMs.
A model constraints formula. See ergm for
details. Note that only constraints that do not induce dyadic
dependence can be handled by ergm.bridge.dindstart.llk.
A vector of coefficients for the configuration of interest.
A one-sided formula with the dyad-independent model to use as a
starting point. Defaults to the dyad-independent terms found in the
formula object with an overal density term (edges)
added if not redundant.
Parameter configuration for the dyad-independent starting
point. Defaults to the MLE of dind.
An optional network object to start
the Markov chain. If omitted, the default is the left-hand-side of
the object.
Further arguments to ergm.bridge.llr and simulate.formula.ergm.
Whether only the estiamted log-likelihood should be returned. (Defaults to TRUE.)
Control parameters. See control.ergm.bridge.
If llkonly=TRUE, returns the scalar
log-likelihood. Otherwise, returns a copy of the list returned by
ergm.bridge.llr in addition to the following components:
The log-likelihood of the dyad-independence model.
The estimated log-likelihood.
Hunter, D. R. and Handcock, M. S. (2006) Inference in curved exponential family models for networks, Journal of Computational and Graphical Statistics.