repetitive "Subject 1 is Singular" error.

Post technical questions about making Pmetrics carry out a particular task.
Post Reply
isegarra
Posts: 12
Joined: Mon Nov 10, 2014 10:45 am
Location: Barcelona (SPAIN)

repetitive "Subject 1 is Singular" error.

Post by isegarra » Tue Sep 29, 2015 3:28 am

Hi all,

I am running the IT2B engine (Pmetrics vesion 1.4.1 on a win7, 32 bits system) and got the error below at cycle 10. If I limit the cycles to 9, then it is ok but does not converge:

ERROR REPORT

THE CURRENT ESTIMATE OF THE COVARIANCE MATRIX OF THE PARAMETER ESTIMATES FOR SUBJECT 1 IS "SINGULAR". THIS IS DUE TO AN ILL-CONDTIONED PROBLEM. THE PROGRAM NOW STOPS. PLEASE RE-EXAMINE YOUR PATIENT DATA FILES, ALONG WITH YOUR INPUT INSTRUCTIONS TO CHECK FOR ANY INCONSISTENCIES.

I have removed subject 1 from the run adding

Code: Select all

exclude=c(201)
(subject 1 ID is 201), then run again and got the same error for subject 1 again. So I exclude the new subject 1:

Code: Select all

exclude=c(201,225)
and run it. But got the same error again.

THE CURRENT ESTIMATE OF THE COVARIANCE MATRIX OF THE PARAMETER ESTIMATES FOR SUBJECT 1 IS "SINGULAR". THIS IS DUE TO AN ILL-CONDTIONED PROBLEM. THE PROGRAM NOW STOPS. PLEASE RE-EXAMINE YOUR PATIENT DATA FILES, ALONG WITH YOUR INPUT INSTRUCTIONS TO CHECK FOR ANY INCONSISTENCIES.

So I keep excluding removing the following subject 1 and so on

Code: Select all

(exclude=c(201, 226, 225)
which are the ID for the subjects. It does not matter how many subsequent subjects 1 I remove, it gives that error again.

Any suggestion?

Thanks!

Ignacio
Ignacio Segarra, PhD.
Clinical Pharmacy and Pharmacotherapy Research Group. Faculty of Pharmacy.
University of Barcelona.

Post Reply