Next: Diagonalisation of outer product
Up: Estimation of OU processes
Previous: Restricted estimation
The most general, time dependent linear ODE
 |
(86) |
where
and
. The
ansatz
leads to the (formal) solution
 |
(87) |
With this result it is easy to guess a solution for the non-stationary
OU-process
 |
(88) |
as
 |
(89) |
Markus Mayer
2009-06-22