control.ergm: Auxiliary for Controlling ERGM Fitting

Description

Auxiliary function as user interface for fine-tuning 'ergm' fitting.

Usage

control.ergm(drop=TRUE,
             init=NULL,
             init.method=NULL,
                       
             main.method=c("MCMLE","Robbins-Monro",
               "Stochastic-Approximation","Stepping"),
             force.main=FALSE,
             main.hessian=TRUE,
             MPLE.max.dyad.types=1e+6, 
             MPLE.samplesize=50000,                       
             MPLE.type=c("glm", "penalized"),
                      
             MCMC.prop.weights="default", 
             MCMC.prop.args=list(),
             MCMC.burnin=10000,
             MCMC.interval=100,
             MCMC.samplesize=10000,
             MCMC.return.stats=TRUE,
             MCMC.burnin.retries=0,
             MCMC.burnin.check.last=1/2,
             MCMC.burnin.check.alpha=0.01,
             MCMC.runtime.traceplot=FALSE,
             MCMC.init.maxedges=20000,
             MCMC.max.maxedges=Inf,
             MCMC.addto.se=TRUE,
             MCMC.compress=FALSE,
             MCMC.packagenames=c(),
             SAN.maxit=10,
             SAN.control=control.san(
                         coef=init,
                         SAN.prop.weights=MCMC.prop.weights,
                         SAN.prop.args=MCMC.prop.args,
                         SAN.init.maxedges=MCMC.init.maxedges,
                         SAN.burnin=MCMC.burnin*10,
                         SAN.interval=MCMC.interval,
                         SAN.packagenames=MCMC.packagenames,
                         parallel=parallel,
                         parallel.type=parallel.type,
                         parallel.version.check=parallel.version.check),
             MCMLE.maxit=20,
             MCMLE.conv.min.pval=0.5,
             MCMLE.NR.maxit=100,
             MCMLE.NR.reltol=sqrt(.Machine$double.eps),
             obs.MCMC.samplesize=MCMC.samplesize,
             obs.MCMC.interval=MCMC.interval,
             obs.MCMC.burnin=MCMC.burnin,
             MCMLE.check.degeneracy=FALSE,
             MCMLE.MCMC.precision=0.05,
             MCMLE.metric=c("lognormal", "Median.Likelihood",
               "EF.Likelihood", "naive"),
             MCMLE.method=c("BFGS","Nelder-Mead"),
             MCMLE.trustregion=20,
             MCMLE.dampening=FALSE,
             MCMLE.dampening.min.ess=20,
             MCMLE.dampening.level=0.1,
             MCMLE.steplength=0.5,
             MCMLE.adaptive.trustregion=3,
             MCMLE.adaptive.epsilon=0.01,
             MCMLE.sequential=TRUE,
             MCMLE.density.guard.min=10000,
             MCMLE.density.guard=exp(3),

             SA.phase1_n=NULL, 
             SA.initial_gain=NULL, 
             SA.nsubphases=MCMLE.maxit, 
             SA.niterations=NULL, 
             SA.phase3_n=NULL,
             SA.trustregion=0.5,
             RM.phase1n_base=7,
             RM.phase2n_base=100,
             RM.phase2sub=7,
             RM.init_gain=0.5,
             RM.phase3n=500,
             Step.MCMC.samplesize=100,
             Step.maxit=50,
             Step.gridsize=100,
             loglik.control=control.logLik.ergm(),
             seed=NULL,
             parallel=0,
             parallel.type=NULL,
             parallel.version.check=TRUE,
             
             ...)

Arguments

drop

Logical: If TRUE, terms whose observed statistic values are at the extremes of their possible ranges are dropped from the fit and their corresponding parameter estimates are set to plus or minus infinity, as appropriate. This is done because

init

numeric or NA vector equal in length to the number of parameters in the model or NULL (the default); the initial values for the estimation and coefficient offset terms. If NULL is passed, all of the initi

Value

A list with arguments as components.

item

init.method
main.method
force.main
main.hessian
MPLE.max.dyad.types
MPLE.samplesize
MPLE.type
MCMC.prop.weights
MCMC.prop.args
MCMC.burnin
MCMC.interval
MCMC.samplesize
MCMC.return.stats
MCMC.burnin.retries
MCMC.burnin.check.last
MCMC.burnin.check.alpha
MCMC.runtime.traceplot
MCMC.init.maxedges, MCMC.max.maxedges
MCMC.addto.se
MCMC.compress
MCMC.packagenames
SAN.maxit
SAN.control
MCMLE.maxit
MCMLE.conv.min.pval
MCMLE.NR.maxit
MCMLE.NR.reltol
obs.MCMC.samplesize,obs.MCMC.burnin,obs.MCMC.interval
MCMLE.check.degeneracy
MCMLE.MCMC.precision
MCMLE.metric
MCMLE.method
MCMLE.trustregion
MCMLE.dampening
MCMLE.dampening.min.ess
MCMLE.dampening.level
MCMLE.steplength
MCMLE.adaptive.trustregion
MCMLE.adaptive.epsilon
MCMLE.sequential
MCMLE.density.guard.min, MCMLE.density.guard
SA.phase1_n
SA.initial_gain
SA.nsubphases
SA.niterations
SA.phase3_n
SA.trustregion
RM.phase1n_base
RM.phase2n_base
RM.phase2sub
RM.init_gain
RM.phase3n
Step.MCMC.samplesize
Step.maxit
Step.gridsize
loglik.control
seed
parallel
parallel.type
parallel.version.check
...

code

ergm

eqn

$1/N$

link

parallel processing

Details

This function is only used within a call to the ergm function. See the usage section in ergm for details.

References

Snijders, T.A.B. (2002), Markov Chain Monte Carlo Estimation of Exponential Random Graph Models. Journal of Social Structure. Available fromhttp://www.cmu.edu/joss/content/articles/volume3/Snijders.pdf.
Firth (1993), Bias Reduction in Maximum Likelihood Estimates. Biometrika, 80: 27-38.
Hunter, D. R. and M. S. Handcock (2006), Inference in curved exponential family models for networks. Journal of Computational and Graphical Statistics, 15: 565-583.
Hummel, R. M., Hunter, D. R., and Handcock, M. S. (2012), Improving Simulation-Based Algorithms for Fitting ERGMs, Journal of Computational and Graphical Statistics, to appear.