Extract summary statistics for the posterior covariance matrix which have been stored during sampling
runningcovmat extracts summary statistics from the model-implied
covariance matrix
from an fsvdraws object for one point in time.
runningcovmat(x, i, statistic = "mean", type = "cov")
x |
Object of class |
i |
A single point in time. |
statistic |
Indicates which statistic should be extracted. Defaults
to |
type |
Indicates whether covariance ( |
Matrix containing the requested covariance matrix summary statistic.
Other extractors:
cormat.fsvdraws(),
covmat.fsvdraws(),
runningcormat()
set.seed(1)
sim <- fsvsim(n = 500, series = 3, factors = 1) # simulate
res <- fsvsample(sim$y, factors = 1) # estimate
cov100mean <- runningcovmat(res, 100) # extract mean at t = 100
cov100sd <- runningcovmat(res, 100, statistic = "sd") # extract sd
lower <- cov100mean - 2*cov100sd
upper <- cov100mean + 2*cov100sd
true <- covmat(sim, 100) # true value
# Visualize mean +/- 2sd and data generating values
par(mfrow = c(3,3), mar = c(2, 2, 2, 2))
for (i in 1:3) {
for (j in 1:3) {
plot(cov100mean[i,j], ylim = range(lower, upper), pch = 3,
main = paste(i, j, sep = ' vs. '), xlab = '', ylab = '')
lines(c(1,1), c(lower[i,j], upper[i,j]))
points(true[i,j,1], col = 3, cex = 2)
}
}Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.