gden
computes the density of the graphs indicated by g
in collection dat
, adjusting for the type of graph in question.
gden(dat, g=NULL, diag=FALSE, mode="digraph", ignore.eval=FALSE)
one or more input graphs.
integer indicating the index of the graphs for which the density is to be calculated (or a vector thereof). If g==NULL
(the default), density is calculated for all graphs in dat
.
boolean indicating whether or not the diagonal should be treated as valid data. Set this true if and only if the data can contain loops. diag
is FALSE
by default.
string indicating the type of graph being evaluated. "digraph" indicates that edges should be interpreted as directed; "graph" indicates that edges are undirected. mode
is set to "digraph" by default.
logical; should edge values be ignored when calculating density?
The graph density
The density of a graph is here taken to be the sum of tie values divided by the number of possible ties (i.e., an unbiased estimator of the graph mean); hence, the result is interpretable for valued graphs as the mean tie value when ignore.eval==FALSE
. The number of possible ties is determined by the graph type (and by diag
) in the usual fashion.
Where missing data is present, it is removed prior to calculation. The density/graph mean is thus taken relative to the observed portion of the graph.
Wasserman, S., and Faust, K. (1994). Social Network Analysis: Methods and Applications. Cambridge: Cambridge University Press.
# NOT RUN {
#Draw three random graphs
dat<-rgraph(10,3)
#Find their densities
gden(dat)
# }
Run the code above in your browser using DataLab