Is it possible to revert in tab_model() to show the latent variable estimate of the ICC again for multilevel logistic regression
$ICC = \frac{\sigma^2}{\sigma^2 + \frac{\pi^{2}}{3} }$
library(lme4)
library(sjPlot)
gm1 <- glmer(cbind(incidence, size - incidence) ~ period + (1 | herd),
data = cbpp, family = binomial)
tab_model(gm1)
The latent variable estimates is now given by performance::icc() when by_group = TRUE is set. Not sure why.
# shows the default result from icc()
performance::icc(gm1)
# Intraclass Correlation Coefficient
#
# Adjusted ICC: 0.008
# Conditional ICC: 0.007
# perhaps better to show the by_group = TRUE results?
performance::icc(gm1, by_group = TRUE)
# # ICC by Group
#
# Group | ICC
# -------------
# herd | 0.124
Is it possible to revert in
tab_model()
to show the latent variable estimate of the ICC again for multilevel logistic regression $ICC = \frac{\sigma^2}{\sigma^2 + \frac{\pi^{2}}{3} }$The latent variable estimates is now given by
performance::icc()
whenby_group = TRUE
is set. Not sure why.