RE: Error in table step
Dear Mark,
I've very recently run into the same issue and in my case removing the
individual didn't change one bit; it just came up with a new individual. I also
implemented all the ususal checks with no avail. In my case I'm convinced it
had to do with an over-parameterized model where fixing the IIV of an
ill-defined parameter made the error go away, or at least most of the times
with appropriate starting values. It did make the OFV increase substantially
but that's the price I was willing to pay... (FOCE and likelihood estimation by
the way, so indeed not specific to SAEM).
Good luck!
Rik Schoemaker, PhD
Occams BV
Malandolaan 10
1187 HE Amstelveen
The Netherlands
http://www.occams.eu/
+31 20 441 6410
[email protected]<mailto:[email protected]>
[cid:[email protected]]
Quoted reply history
From: [email protected] [mailto:[email protected]] On
Behalf Of Mark Sale
Sent: 27 September 2015 15:29
To: [email protected]
Subject: [NMusers] Error in table step
Dear colleagues:
I have a very large model (lots of ODEs, lots of data, long duration), running
parallel across several machines, using SAEM. Runs reasonably well. But,
fails the $TABLE with this error:
0PROGRAM TERMINATED BY FNLETA
0PRED EXIT CODE = 1
0INDIVIDUAL NO. 3 ID= 5.10000000000000E+01 (WITHIN-INDIVIDUAL) DATA
REC NO. 1
THETA=
0.00E+00 1.19E+00 2.59E-01 5.68E+00 2.64E-01 5.69E+00 2.35E+00
4.17E-01 4.20E-04 6.50E-01
3.98E-01 1.86E-01 -3.50E-01 -2.09E-01 -1.87E+00 2.09E-01 1.85E-01
-1.90E-01 1.30E+00 4.82E-01
0.00E+00 9.54E-01 1.34E+03 1.19E+00 3.44E-01 1.78E+03
OCCURS DURING SEARCH FOR ETA AT INITIAL VALUE, ETA=0
F OR DERIVATIVE RETURNED BY PRED IS INFINITE (INF) OR NOT A NUMBER (NAN).
0PROGRAM TERMINATED BY FNLETA
MESSAGE ISSUED FROM TABLE STEP
All the THETA values of 0.00 are fixed to that value. All the other values are
very reasonable.
So, I don't get any tables, can't to a VPC etc. I've tried running FOCE, no
better. Tried error checking that F is always positive, tried EXIT if F is
very small, I have the NOABORT option set (but I don't think that is relevant
in the $TABLE step).
I assume it is crashing calculating the conditional ETAs (don't know why it
does OK in estimation). PRDERR only has the small number of error from the
estimation
Anyone seen this error, any suggestions on how to get rid of it (other than
removeing subject 51)?
Mark
Mark Sale M.D.
Vice President, Modeling and Simulation
Nuventra, Inc. (tm)
2525 Meridian Parkway, Suite 280
Research Triangle Park, NC 27713
Office (919)-973-0383
[email protected]<[email protected]>
http://www.nuventra.com
Empower your Pipeline
CONFIDENTIALITY NOTICE The information in this transmittal (including
attachments, if any) may be privileged and confidential and is intended only
for the recipient(s) listed above. Any review, use, disclosure, distribution or
copying of this transmittal, in any form, is prohibited except by or on behalf
of the intended recipient(s). If you have received this transmittal in error,
please notify me immediately by reply email and destroy all copies of the
transmittal.