sn (version 0.4-18)

msn.marginal: Marginal components of a multivariate skew-normal distribution

Description

Computes the marginal distribution of a subset of components of a multivariate skew-normal distribution.

Usage

msn.marginal(xi=rep(0, length(alpha)), Omega, alpha, comp=1:d, dp=NULL)

Arguments

xi

a numeric vector of length d, say, giving the location parameter.

Omega

a covariance matrix of dimension (d,d).

alpha

a numeric vector of length d, which regulates the shape of the density.

comp

a vector containing a subset of 1:d selecting the components of the marginal distribution. A permutation of 1:d is allowed, and the components of comp do not need to be sorted.

dp

a list containing the components xi, Omega, alpha, contaning quantities as described above; if dp is specified, then the indicidual components must not be in the calling statement

Value

• A list containing components xi, Omega, alpha with the parameters of the marginal distribution. If length(comp) is equal to m, say, then the new components are of size m, (m,m), m, respectively.

Background

See the reference below for background information.

Details

Typical usages are msn.marginal(xi, Omega, alpha, comp) msn.marginal(dp=, comp)

References

Azzalini, A. and Capitanio, A. (1999). Statistical applications of the multivariate skew-normal distribution. J.Roy.Statist.Soc. B 61, 579--602.

See Also

dmsn, msn.conditional, msn.affine

Examples

xi <- c(10,0,-30)
Omega <- 5*diag(3)+outer(1:3,1:3)
alpha <- c(1,-3,5)
msn.marginal(xi,Omega,alpha,c(3,1))
msn.marginal(dp=list(xi=xi,Omega=Omega,alpha=alpha), comp=3)