annotate toolboxes/FullBNT-1.0.7/KPMstats/matrix_T_pdf.m @ 0:cc4b1211e677
tip
initial commit to HG from
Changeset:
646 (e263d8a21543) added further path and more save "camirversion.m"
| author |
Daniel Wolff |
| date |
Fri, 19 Aug 2016 13:07:06 +0200 |
| parents |
|
| children |
|
| rev |
line source |
|
Daniel@0
|
1 function p = matrix_T_pdf(A, M, V, K, n)
|
|
Daniel@0
|
2 % MATRIX_T_PDF Evaluate the density of a matrix under a Matrix-T distribution
|
|
Daniel@0
|
3 % p = matrix_T_pdf(A, M, V, K, n)
|
|
Daniel@0
|
4
|
|
Daniel@0
|
5 % See "Bayesian Linear Regression", T. Minka, MIT Tech Report, 2001
|
|
Daniel@0
|
6
|
|
Daniel@0
|
7 [d m] = size(K);
|
|
Daniel@0
|
8 is = 1:d;
|
|
Daniel@0
|
9 c1 = prod(gamma((n+1-is)/2)) / prod(gamma((n-m+1-is)/2));
|
|
Daniel@0
|
10 c2 = det(K)^(d/2) / det(pi*V)^(m/2); %% pi or 2pi?
|
|
Daniel@0
|
11 p = c1 * c2 * det((A-M)'*inv(V)*(A-M)*K + eye(m))^(-n/2);
|
|
Daniel@0
|
12
|
