simulate.btergm {btergm}

Simulate Networks from a btergm Object

Description

Simulate networks from a btergm object using MCMC sampler.

Simulate networks from an mtergm object using MCMC sampler.

Usage

## S3 method for class 'btergm'
simulate(
  object,
  nsim = 1,
  seed = NULL,
  index = NULL,
  formula = getformula(object),
  coef = object@coef,
  verbose = TRUE,
  ...
)

## S3 method for class 'mtergm'
simulate(
  object,
  nsim = 1,
  seed = NULL,
  index = NULL,
  formula = getformula(object),
  coef = object@coef,
  verbose = TRUE,
  ...
)

Arguments

object

A btergm or mtergm object, resulting from a call of the btergm or mtergm function.

nsim

The number of networks to be simulated. Note that for values greater than one, a network.list object is returned, which can be indexed just like a list object, for example mynetworks[[1]] for the first simulated network in the object mynetworks.

seed

Random number integer seed. See set.seed.

index

Index of the network from which the new network(s) should be simulated. The index refers to the list of response networks on the left-hand side of the model formula. Note that more recent networks are located at the end of the list. By default, the last (= most recent) network is used.

formula

A model formula from which the new network(s) should be simulated. By default, the formula is taken from the btergm object.

coef

A vector of parameter estimates. By default, the coefficients are extracted from the given btergm object.

verbose

Print additional details while running the simulations?

...

Further arguments are handed over to the simulate_formula function in the ergm package.

Details

The simulate.btergm function is a wrapper for the simulate_formula function in the ergm package (see help("simulate.ergm")). It can be used to simulate new networks from a btergm object. The index argument specifies from which of the original networks the new network(s) should be simulated. For example, if object is an estimation based on cosponsorship networks from the 99th to the 107th Congress (as in Desmarais and Cranmer 2012), and the cosponsorship network in the 108th Congress should be predicted using the simulate.btergm function, then the argument index = 9 should be passed to the function because the network should be based on the 9th network in the list (that is, the latest network, which is the cosponsorship network for the 107th Congress). Note that all relevant objects (the networks and the covariates) must be present in the workspace (as was the case during the estimation of the model).

References

Desmarais, Bruce A. and Skyler J. Cranmer (2012): Statistical Mechanics of Networks: Estimation and Uncertainty. Physica A 391: 1865–1876. doi:10.1016/j.physa.2011.10.018.

Leifeld, Philip, Skyler J. Cranmer and Bruce A. Desmarais (2018): Temporal Exponential Random Graph Models with btergm: Estimation and Bootstrap Confidence Intervals. Journal of Statistical Software 83(6): 1–36. doi:10.18637/jss.v083.i06.

Examples

## Not run: 
# fit a TERGM to some toy data
library("network")
set.seed(5)
networks <- list()
for(i in 1:10){            # create 10 random networks with 10 actors
  mat <- matrix(rbinom(100, 1, .25), nrow = 10, ncol = 10)
  diag(mat) <- 0           # loops are excluded
  nw <- network(mat)       # create network object
  networks[[i]] <- nw      # add network to the list
}
covariates <- list()
for (i in 1:10) {          # create 10 matrices as covariate
  mat <- matrix(rnorm(100), nrow = 10, ncol = 10)
  covariates[[i]] <- mat   # add matrix to the list
}
fit <- btergm(networks ~ edges + istar(2) +
                edgecov(covariates), R = 100)

# simulate 12 new networks from the last (= 10th) time step
sim1 <- simulate(fit, nsim = 12)

# simulate 1 network from the first time step
sim2 <- simulate(fit, index = 1)

# simulate network from t = 5 with larger covariate coefficient
coefs <- coef(fit)
coefs["edgecov.covariates[[i]]"] <- 0.5
sim3 <- simulate(fit, index = 5, coef = coefs)

## End(Not run)