latentnet (version 2.0)

ergmm.control: Auxiliary for Controlling ERGMM Fitting

Description

Auxiliary function as user interface for ergmm fitting. Typically only used when calling ergmm. It is used to set parameters that affect the sampling but do not affect the posterior distribution.

Usage

ergmm.control(samplesize=2000,
                        burnin=1000,
                        interval=10,
                        threads=1,
                        mle.maxit=400,
                        tune=FALSE,
                        tuning.runs=100,
                        tuning.runsize=8,
                        Z.delta=0.4,
                        Z.tr.delta=0.4,
                        Z.scl.delta=0.02,
                        beta.delta=0.4,
                        store.burnin=FALSE)

Arguments

samplesize

The number of draws to be taken from the posterior distribution.

burnin

The number of MCMC iterations to be discarded.

interval

The number of iterations between consecutive draws.

threads

The number of chains to run. If greater than 1, package snowFT is used to take advantage of any multiprocessing or distributed computing capabilities that may be available.

mle.maxit

Maximum number of iterations for computing the starting values, posterior modes, MLEs, MKL estimates, etc..

tune

If TRUE, the proposal variances are tuned before burnin and again before sampling begins. The tuner is somewhat experimental.

tuning.runs

Number of points at which to evaluate tuning.

tuning.runsize

Number of iterations per point.

Z.delta

Standard deviation of the proposal for the jump in the individual latent space position, or its starting value for the tuner.

beta.delta

Standard deviation of the proposal for the jump in the covariate coefficients, or its starting value for the tuner.

Z.tr.delta

Standard deviation of the proposal for the the translating of all latent space positions, or its starting value for the tuner.

Z.scl.delta

Standard deviation of the log of the proposal for the scaling of latent space positions, or its starting value for the tuner.

store.burnin

If TRUE, the samples from the burnin are also stored and returned, to be used in MCMC diagnostics.

Value

• A list with the arguments as components.

See Also

ergmm

Examples

data(sampson)
## Shorter run than default.
ergmm(samplike~latent(d=2,G=3),control=ergmm.control(samplesize = 200))