gofit.lolog function

Goodness of Fit Diagnostics for a LOLOG fit

## S3 method for class 'lolog'
gofit(object, formula, nsim = 100, ...)

Arguments

• object: the object to evaluate
• formula: A formula specifying the statistics on which to evaluate the fit
• nsim: The number of simulated statistics
• ...: additional parameters

Examples

library(network)
data(ukFaculty)

# Delete vertices missing group
delete.vertices(ukFaculty, which(is.na(ukFaculty %v% "Group")))

# A dyad independent model
fitind <- lolog(ukFaculty ~ edges() + nodeMatch("GroupC") + nodeCov("GroupC"))
summary(fitind)

# Check gof on degree distribution (bad!)
gind <- gofit(fitind, ukFaculty ~ degree(0:50))
gind
plot(gind)

#check gof on esp distribution (bad!)
gind <- gofit(fitind, ukFaculty ~ esp(0:25))
gind
plot(gind)

## Not run:

#include triangles and 2-stars (in and out)
fitdep <- lolog(ukFaculty ~ edges() + nodeMatch("GroupC") + nodeCov("GroupC") + 
                triangles + star(2, direction="in") + star(2, direction="out"), nsamp=1500)
summary(fitdep)

# Check gof on (in + out) degree distribution (good!)
gdep <- gofit(fitdep, ukFaculty ~ degree(0:50))
gdep
plot(gdep)

#check gof on esp distribution (good!)
gdep <- gofit(fitdep, ukFaculty ~ esp(0:25))
gdep
plot(gdep)
## End(Not run)