sim_matgaussian {bvhar}R Documentation

Generate Matrix Normal Random Matrix

Description

This function samples one matrix gaussian matrix.

Usage

sim_matgaussian(mat_mean, mat_scale_u, mat_scale_v)

Arguments

mat_mean

Mean matrix

mat_scale_u

First scale matrix

mat_scale_v

Second scale matrix

Details

Consider n x k matrix Y1,,YnMN(M,U,V)Y_1, \ldots, Y_n \sim MN(M, U, V) where M is n x k, U is n x n, and V is k x k.

  1. Lower triangular Cholesky decomposition: U=PPTU = P P^T and V=LLTV = L L^T

  2. Standard normal generation: s x m matrix Zi=[zijN(0,1)]Z_i = [z_{ij} \sim N(0, 1)] in row-wise direction.

  3. Yi=M+PZiLTY_i = M + P Z_i L^T

This function only generates one matrix, i.e. Y1Y_1.

Value

One n x k matrix following MN distribution.


[Package bvhar version 2.0.1 Index]