rmixmultnorm: Random draw from mixture of multivariate normals.

In dcgerard/UltimateDeconvolution: Deconvolution Problem in Multivariate Gaussian Mixtures

Description

It is assumed that the mixing covariances are rank-1 (with their square roots in v_mat) and the observation covariances are diagonal (with their variances in s_mat).

Usage

rmixmultnorm(s_mat, v_mat, pi_vec)

Arguments

s_mat	A matrix of variances (NOT standard deviations). The rows index the observations and the columns index the variables.
v_mat	A matrix of square-roots of the rank-1 mixing covariance matrices. The columns index the mixing components, the rows index the variables.
pi_vec	A vector of mixture proportions.

Details

The number of observations drawn is equal to nrow(s_mat).

Author(s)

David Gerard

See Also

dmixlike

dcgerard/UltimateDeconvolution documentation built on May 15, 2019, 1:24 a.m.