Summarises the posterior of the OTU covariance matrix from a ZI_MLN() fit.
By default the marginal covariance
\(\Omega = \Lambda\Lambda' + (\sigma^2 + u_s^2) I\) is returned (the one
whose correlation is posterior_correlation()). Set marginal = FALSE for the
interaction covariance \(\Sigma = \Lambda\Lambda' + \sigma^2 I\), which
excludes the subject random-effect variance.
Usage
posterior_covariance(fit, marginal = TRUE, ci = FALSE, prob = c(0.025, 0.975))Arguments
- fit
A list returned by
ZI_MLN().- marginal
Logical; add the subject random-effect variance \(u_s^2\) to the diagonal (
TRUE, default, giving \(\Omega\)) or not (FALSE, giving \(\Sigma\)).- ci, prob
As in
posterior_correlation().
Value
A J x J posterior-mean covariance matrix, or a list of
mean/lower/upper matrices when ci = TRUE.
Examples
# \donttest{
sim <- simulate_zimln(n = 20, J = 20, K = 2, seed = 1)
fit <- ZI_MLN(sim$Y, m = sim$m, M = sim$M, niter = 400, burnin = 200)
Sigma <- posterior_covariance(fit, marginal = FALSE)
# }