Depends. I have come across cases with large variances where you get an
overflow to zero in SAEM. It is however not very likely with a
closed-form PK model.
http://pd-value.com
jer...@pd-value.com
@PD_value
+31 6 23118438
-- More value out of your data!
On 26-01-2024 16:41, Leonid Gibiansky wrote:
This part is easy to solve: if you do it in log space, Q will always
be positive, no PROTECT is needed (and I am not sure it is relevant in
the case when Q is going to be negative).
On 1/26/2024 10:27 AM, Jeroen Elassaiss-Schaap (PD-value B.V.) wrote:
Dear Omar,
What you describe is not that strange. It can happen because SAEM
does random sampling whereas FOCE-I uses a directed search. Therefore
extreme values can occur with SAEM. Please refer to the section I60
of user guide for v7+ "Stable Routines for Estimation Methods and
Automated Protection Against Floating Point Exceptions" for more
detail, but you could start with including
$ABBR PROTECT
which probably is adequate in your case.
Hope this helps,
Jeroen
http://pd-value.com
jer...@pd-value.com
@PD_value
+31 6 23118438
-- More value out of your data!
On 26-01-2024 16:01, Elashkar, Omar I. wrote:
Hello NMusers,
I have created a model that fit ok with FOCE+I. When I try to fit
with SAEM, I get the following error:
"""
ERROR IN TRANS4 ROUTINE: Q IS ZERO
Elapsed estimation time in seconds: 0.00
INDIVIDUAL OBJECTIVE FUNCTION VALUES ARE ALL ZERO. PROBLEM ENDED
"""
The data is very small, but the model seems acceptable from
bootstrap on FOCE+I. Any ideas are appreciated!
Thank you,
Omar
*Omar Elashkar, *B.Pharm, MSc
Graduate Assistant
University of Florida | College of Pharmacy
