Because the Kalman Filter is an occasion where large numbers of matrices get together to celebrate their existence, can somebody please clarify the following for me:

Given starting values for the parameters, and all the rest, the Kalman filter runs, and it gives the first log-likelihood value series. Then the MLE takes over, but it immediately finds that

"matrix is not positive definite".

The question is: which matrix is the message referring to?

Output below:

<<

loglikelihood = -257.320305306
Parameters:     -0.98707     0.75974     -2.5877    -0.46878    -0.27031     0.84507
                -0.15738  -0.0069893   0.0031079     0.12495     0.68615    0.024908
                0.021948    -0.26022      2.1582    -0.15156      3.8203  -0.0063071
                 0.13977      1.0020    -0.14038      3.3118   0.0056091   0.0085330
                0.038741   0.0069463     0.00000     0.00000    -0.40048     -1.4917
                  49.000      49.000      49.000      49.000      1.0000      1.0000
                0.015000     0.10000    -0.80000
Gradients:       0.00000     0.00000     0.00000     0.00000     0.00000     0.00000
                 0.00000     0.00000     0.00000     0.00000     0.00000     0.00000
                 0.00000     0.00000     0.00000     0.00000     0.00000     0.00000
                 0.00000     0.00000     0.00000     0.00000     0.00000     0.00000
                 0.00000     0.00000     0.00000     0.00000     0.00000     0.00000
                 0.00000     0.00000     0.00000     0.00000     0.00000     0.00000
                 0.00000     0.00000     0.00000 (norm 0.00e+000)
Tolerance = 1.81899e-012

Matrix is not positive definite

Error executing script: halting

>>

-- 
Alecos Papadopoulos PhD
Athens University of Economics and Business
web: alecospapadopoulos.wordpress.com/
skype:alecos.papadopoulos