Optimization of the hyperparameters using a sequence of subfunctions.
1 2 3 4 5  optimal_params (expt, LoF, start_hp, option = "a", ...)
optimal_B (expt, LoF, start_hp, option = "a", verbose=FALSE, ...)
optimal_identical_B(expt, LoF, start_hp, verbose=FALSE, ...)
optimal_diag_M (expt, LoF, start_hp)
optimal_M (expt, LoF, start_hp, ...)

expt 
Object of class 
LoF 
List of functions 
start_hp 
Start value for the hyperparameters, an object of class 
option 
In function

verbose 
In function 
... 
Further arguments passed to the optimization routine 
The userfriendly wrapper function is optimal_params()
. This
calls function optimal_B()
first, as most of the analysis is
conditional on B
. Then optimal_diag_M()
is called; this
places the maximum likelihood estimate for sigma^2 on
the diagonal of M
. Finally, optimal_M()
is called,
which assigns the offdiagonal elements of M
.
Each of the subfunctions returns an object appropriate for insertion
into a mhp
object.
The “meat” of optimal_params()
is
1 2 3 4 
See how object out
is modified sequentially, it being used as a
start point for the next function.
Returns a mhp
object.
Function optimal_diag_M()
uses MLEs for the diagonals, but using
each type of observation separately. It is conceivable that there is
information that is not being used here.
Robin K. S. Hankin
1 2 3 
Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.
All documentation is copyright its authors; we didn't write any of that.