This function samples normal inverse-wishart matrices.
sim_mniw(num_sim, mat_mean, mat_scale_u, mat_scale, shape, u_prec = FALSE)Number to generate
Mean matrix of MN
First scale matrix of MN
Scale matrix of IW
Shape of IW
If TRUE, use mat_scale_u as its inverse. By default, FALSE.
Consider \((Y_i, \Sigma_i) \sim MIW(M, U, \Psi, \nu)\).
Generate upper triangular factor of \(\Sigma_i = C_i C_i^T\) in the upper triangular Bartlett decomposition.
Standard normal generation: n x k matrix \(Z_i = [z_{ij} \sim N(0, 1)]\) in row-wise direction.
Lower triangular Cholesky decomposition: \(U = P P^T\)
\(A_i = M + P Z_i C_i^T\)