summary.statistics {ergm} | R Documentation |
Used to calculate the specified
statistics for an observed network if its argument is a formula for an
ergm
.
See ergm-terms
for more information on the statistics that may
be specified.
## S3 method for class 'formula': summary.statistics(object, ..., drop=FALSE, basis=NULL) ## S3 method for class 'ergm': summary.statistics(object, ..., drop=FALSE, basis=NULL)
object |
an R object. It is either an R formula object
(see above) or an
ergm model object.
In the latter case, summary.statistics is called for the
object$formula object.
In the former case, object is of the form
y ~ <model terms> ,
where y is a network object or a matrix that can be
coerced to a network object. For the details on the possible
<model terms> , see ergm-terms . To create a
network object in R, use the network() function,
then add nodal attributes to it using the %v%
operator if necessary.
|
drop |
logical: Should terms whose observed statistics are extreme among the set of all possible network statistics (which result in nonexistent MLEs) be dropped? |
basis |
An optional network object relative to which
the global statistics should be calculated. |
... |
further arguments passed to or used by methods. |
If object
is of class formula
, then
summary
may be used in lieu of summary.statistics
because summary.formula
calls the summary.statistics
function.
The function actually cumulates the change statistics when removing edges
from the observed network one by one until the empty network results.
Since each model term has a prespecified value (zero by default) for the
corresponding statistic(s) on an empty network, these change statistics
give the absolute statistics on the original network.
A vector of statistics measured on the network.
ergm, network, ergm-terms
# # Lets look at the Florentine marriage data # data(florentine) # # test the summary.statistics function # summary(flomarriage ~ edges + kstar(2)) m <- as.matrix(flomarriage) summary(m ~ edges) # twice as large as it should be summary(m ~ edges, directed=FALSE) # Now it's correct