gmodel.block function

Generate binary random graphs based on stochastic blockmodel

Given a $(K\times K)$ stochastic blockmodel W, gmodel.block

generates an (n-by-n) binary random graphs. All K blocks have same number of nodes, or almost identical if n is not a multiple of K. Parameter noloop controls whether generated observations have an edge from a node to itself, called a loop.

gmodel.block(W, n, rep = 1, noloop = TRUE)

Arguments

• W: a $(K\times K)$ blockmodel matrix.
• n: the number of nodes for each observation.
• rep: the number of observations to be generated.
• noloop: a logical value; TRUE for graphs without self-loops, FALSE otherwise.

Returns

a named list containing

• G: depending on rep value,

   - **(rep=1)**: an $(n\times n)$ observation, or
   - **(rep>1)**: a length-`rep` list where each element is an observation is an $(n\times n)$ realization from the model.
  

• P: an $(n\times n)$ probability matrix of generating each edge.

Examples

## set inputs
W = matrix(c(0.9,0.2,0.2,0.7),nr=2)
n = 200

## generate 2 observations without self-loops.
out <- gmodel.block(W,n,rep=2,noloop=TRUE)

## visualize generated graphs
opar = par(no.readonly=TRUE)
par(mfrow=c(1,2), pty="s")
image(out$G[[1]]); title("Observation 1")
image(out$G[[2]]); title("Observation 2")
par(opar)

See Also

gmodel.P