| btergm_tidiers {broom} | R Documentation |
This method tidies the coefficients of a bootstrapped temporal exponential random graph model estimated with the xergm. It simply returns the coefficients and their confidence intervals.
## S3 method for class 'btergm' tidy(x, conf.level = 0.95, exponentiate = FALSE, quick = FALSE, ...)
x |
a |
conf.level |
confidence level of the bootstrapped interval |
exponentiate |
whether to exponentiate the coefficient estimates and confidence intervals |
quick |
whether to compute a smaller and faster version, containing
only the |
... |
extra arguments (currently not used) |
There is no augment or glance method
for ergm objects.
A data.frame without rownames.
tidy.btergm returns one row for each coefficient,
with four columns:
term |
The term in the model being estimated and tested |
estimate |
The estimated coefficient |
conf.low |
The lower bound of the confidence interval |
conf.high |
The lower bound of the confidence interval |
if (require("xergm")) {
# Using the same simulated example as the xergm package
# Create 10 random networks with 10 actors
networks <- list()
for(i in 1:10){
mat <- matrix(rbinom(100, 1, .25), nrow = 10, ncol = 10)
diag(mat) <- 0
nw <- network::network(mat)
networks[[i]] <- nw
}
# Create 10 matrices as covariates
covariates <- list()
for (i in 1:10) {
mat <- matrix(rnorm(100), nrow = 10, ncol = 10)
covariates[[i]] <- mat
}
# Fit a model where the propensity to form ties depends
# on the edge covariates, controlling for the number of
# in-stars
btfit <- btergm(networks ~ edges + istar(2) +
edgecov(covariates), R = 100)
# Show terms, coefficient estimates and errors
tidy(btfit)
# Show coefficients as odds ratios with a 99% CI
tidy(btfit, exponentiate = TRUE, conf.level = 0.99)
}