Multivariate version of coda's spectrum0.ar().
Its return value, divided by nrow(cbind(x)), is the estimated
variance-covariance matrix of the sampling distribution of the mean
of x if x is a multivatriate time series with AR(p) structure, with
p determined by AIC.
spectrum0.mvar( x, order.max = NULL, aic = is.null(order.max), tol = .Machine$double.eps^0.5, ... )
x |
a matrix with observations in rows and variables in columns. |
order.max |
maximum (or fixed) order for the AR model. |
aic |
use AIC to select the order (up to |
tol |
drop components until the reciprocal condition number of the transformed variance-covariance matrix is greater than this. |
... |
additional arguments to |
A square matrix with dimension equalling to the number of
columns of x, with an additional attribute "infl" giving the
factor by which the effective sample size is reduced due to
autocorrelation, according to the Vats, Flegal, and Jones (2015)
estimate for ESS.
ar() fails if crossprod(x) is singular,
which is remedied by mapping the variables onto the principal
components of x, dropping redundant dimentions.
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.