[NMusers] RE: Implementing a Kalman Filter based optimization in NONMEM

From: John Warner <John.Warner_at_chdifoundation.org>
Date: Mon, 14 Sep 2015 15:36:15 +0000

Thanks Again Erik
I think your solution solves the problem. I just did a quick experiment an=
d, at least in the simple case that I tried, pred-defined variables do seem=
 to be persistent between calls. So I am not even sure that saving the stat=
e variables to ai's is necessary as long as I do all my work in user define=
d code as opposed to subroutine calls.

So all of this may have been a tempest in a tea pot.

Nonetheless your advice was right on and I thank you for it.

Also thanks to all Kevin and Jason for their helpful comments.
Best
John

John H. Warner, PhD, MBA
Director, Biostatistics
CHDI Management / CHDI Foundation
155 Village Boulevard, Suite 200
Princeton, NJ, 08540
(609) 945-9644: office
(609) 751-7345: cell
(609) 452-2160: fax
john.warner_at_CHDIfoundation.org<mailto:john.warner_at_CHDIfoundation.org>

From: E.Olofsen_at_lumc.nl [mailto:E.Olofsen_at_lumc.nl]
Sent: Monday, September 14, 2015 11:21 AM
To: John Warner; nmusers_at_globomaxnm.com
Subject: RE: Implementing a Kalman Filter based optimization in NONMEM

John,

My understanding is that the variables to be used recursively should be ref=
erenced, so the simplest form is Ai = Ai. (Note that if ETAs are involved=
, also the derivatives of the Ai with respect to the ETAs need to be tracke=
d, but NM-TRAN does this for you).

Best regards,

Erik
________________________________
From: John Warner [John.Warner_at_chdifoundation.org]
Sent: Monday, September 14, 2015 4:38 PM
To: Olofsen, E. (ANST); nmusers_at_globomaxnm.com<mailto:nmusers_at_globomaxnm.co=
m>
Subject: RE: Implementing a Kalman Filter based optimization in NONMEM
Thanks again Erik
I think my code would work with the Ai's alone provided that they persist u=
nchanged between calls to $pred. Do they?

I guess the general question for me is when do user-defined variables persi=
st unchanged between calls to $pred? If the answer is "always" they I am i=
n good shape.
Best
John

John H. Warner, PhD, MBA
Director, Biostatistics
CHDI Management / CHDI Foundation
155 Village Boulevard, Suite 200
Princeton, NJ, 08540
(609) 945-9644: office
(609) 751-7345: cell
(609) 452-2160: fax
john.warner_at_CHDIfoundation.org<mailto:john.warner_at_CHDIfoundation.org>

From: E.Olofsen_at_lumc.nl<mailto:E.Olofsen_at_lumc.nl> [mailto:E.Olofsen_at_lumc.nl=
]
Sent: Monday, September 14, 2015 10:31 AM
To: John Warner; nmusers_at_globomaxnm.com<mailto:nmusers_at_globomaxnm.com>
Subject: RE: Implementing a Kalman Filter based optimization in NONMEM

John,

Would your Kalman filter implementation work with just a $PRED, so without =
a $MODEL? While the A(i) are the amounts in compartments defined in $MODEL,=
 the Ai are user-defined variables.

Best regards,

Erik
________________________________
From: John Warner [John.Warner_at_chdifoundation.org]
Sent: Monday, September 14, 2015 4:09 PM
To: Olofsen, E. (ANST); nmusers_at_globomaxnm.com<mailto:nmusers_at_globomaxnm.co=
m>
Subject: RE: Implementing a Kalman Filter based optimization in NONMEM
Thanks Eric
Yours seems like a very straight-forward and complete solution. However, i=
f I am not mistaken, the Ai variables are created by $model and I am not su=
re that $model can be used by a user supplied $pred. If it can, there rema=
ins the problem of calling the model subroutine. I assume that this would =
be done with verbatim code but I am not sure where to put such a call in my=
 control stream. The documentation (html help files) states that $model is=
 called only once by the PREDPP subroutines that use it. Perhaps I could p=
ut such a call in the $input or $pk records? $PK would seem more logical b=
ut it is not clear that this record is available outside of predPP.

I am very interested to hear any additional responses to this.

Thanks again.

John
John H. Warner, PhD, MBA
Director, Biostatistics
CHDI Management / CHDI Foundation
155 Village Boulevard, Suite 200
Princeton, NJ, 08540
(609) 945-9644: office
(609) 751-7345: cell
(609) 452-2160: fax
john.warner_at_CHDIfoundation.org<mailto:john.warner_at_CHDIfoundation.org>

From: E.Olofsen_at_lumc.nl<mailto:E.Olofsen_at_lumc.nl> [mailto:E.Olofsen_at_lumc.nl=
]
Sent: Monday, September 14, 2015 4:40 AM
To: John Warner; nmusers_at_globomaxnm.com<mailto:nmusers_at_globomaxnm.com>
Subject: RE: Implementing a Kalman Filter based optimization in NONMEM

Dear John,

In the code by Tornoe et al., state variables A(i) are stored in the Ai var=
iables, and retrieved by statements Ai = Ai. Such recursive code is descr=
ibed in NONMEM's help on abbreviated code. Although the A(i) are associated=
 with differential equations, you could perhaps still use such recursive st=
atements, indicating that you want to store and retrieve information?

Best regards,

Erik
________________________________
From: owner-nmusers_at_globomaxnm.com<mailto:owner-nmusers_at_globomaxnm.com> [ow=
ner-nmusers_at_globomaxnm.com] on behalf of John Warner [John.Warner_at_chdifound=
ation.org]
Sent: Sunday, September 13, 2015 11:24 PM
To: nonmem usersgroup
Subject: [NMusers] Implementing a Kalman Filter based optimization in NONME=
M
Dear NONMEM users
I am attempting to implement a Kalman Filter based optimization in NONMEM u=
sing $PRED directly. The method I am attempting to implement is similar i=
n spirit to that presented in Tornoe et. al. (2005) (and the NONMEM 7.3 man=
ual) except that I have no need for a differential equations solver. In e=
ffect I can solve the differential equations analytically but I still need =
to estimate a random walk error term. Adapting the procedure of Tornoe et.=
 al. 2005 seems straight-forward except that, it seems to me, I need to fin=
d a way to store the state vector and associated partial derivatives at the=
 end of a call to $PRED and to retrieve them at the beginning of the next c=
all for the same subject. I assume that something like this must be done b=
y ADVAN6 when differential equations are solved.

I would be very grateful for any advice on this.

Best
John


Tornoe et. al. Stochastic Differential Equations in NONMEM(r): Implementa=
tion, Application, and Comparison with Ordinary Differential Equations Ph=
armaceutical Research, Vol. 22, No. 8, August 2005 2005)



John H. Warner, PhD, MBA
Director, Biostatistics
CHDI Management / CHDI Foundation
155 Village Boulevard, Suite 200
Princeton, NJ, 08540
(609) 945-9644: office
(609) 751-7345: cell
(609) 452-2160: fax
john.warner_at_CHDIfoundation.org<mailto:john.warner_at_CHDIfoundation.org>


Received on Mon Sep 14 2015 - 11:36:15 EDT

This archive was generated by hypermail 2.3.0 : Fri Sep 27 2019 - 16:46:08 EDT