Last data update: 2014.03.03

R: Confidence regions (ellipses) from Markov chain Monte Carlo
confRegionR Documentation

Confidence regions (ellipses) from Markov chain Monte Carlo

Description

Constructs confidence regions (ellipses) from the Markov chain output for the features of interest. Function uses the ellipse package.

Usage

confRegion(mcse.obj, which = c(1,2), level = .95)

Arguments

mcse.obj

the list returned by the mcse.multi command

which

integer vector of length 2 indicating the component for which to make the confidence ellipse. Chooses the first two by default.

level

confidence level for the ellipse

Details

Returns a matrix of x and y coordinates for the ellipse. Use plot function on the matrix to plot the ellipse

Examples

library(mAr)
p <- 3
n <- 1e3
omega <- 5*diag(1,p)

## Making correlation matrix var(1) model
set.seed(100)
foo <- matrix(rnorm(p^2), nrow = p)
foo <- foo %*% t(foo)
phi <- foo / (max(eigen(foo)$values) + 1)
  
out <- as.matrix(mAr.sim(rep(0,p), phi, omega, N = n))
mcerror <- mcse.multi(out)

## Plotting the ellipse
plot(confRegion(mcerror), type = 'l')

Results