Re: How to scale PARAMETERs

Hi, The almost incomprehensible display of parameter estimates in their internally scaled format has been a long standing 'feature' of NONMEM and one that has been suggested for change many times. Perhaps in NONMEM 7? The 'solution' which I think appeared in NONMEM V (described below by Bill) is a quick and dirty fix which is rather clumsy for the user to use. Wings for NONMEM users can get access to these intermediate results and update the control stream used to start the run with the latest values with the command: nmctl /runname/ i The second argument 'i' tells nmctl to get values from a file named INTER.txt in the WFN run results folder. This is not the default name for the file but its name can be easily changed in BLKDAT.for i.e. DATA FNSTP,FNINT,FNERR,FNINTR,FNULL 1/'nul','con','PRDERR','INTER.txt','nul'/ This change makes it easier for Windows users to use their text editors to read the file because it has a meaningful extension. You can stop the INTER file being deleted at the end of the run by this change in CFILES.for: C Stop INTER being deleted at end of run. CLOSE (UN(28)) These changes are made automatically if you use the NMQUAL based NMQ4WFN package to install NONMEM for use with WFN. Best wishes, Nick Bachman, William wrote: > You can find the unscaled parameters at the iterations requested in the PRINT= option of $EST in the INTER file if you specify MSFO as an $EST option. The file exists only during the run (by default). > > ------------------------------------------------------------------------ > > *From:* [EMAIL PROTECTED] [ mailto:[EMAIL PROTECTED] *On Behalf Of [EMAIL PROTECTED] > > *Sent:* Tuesday, August 26, 2008 12:45 PM > *To:* [email protected] > *Subject:* [NMusers] How to scale PARAMETERs > > Hi there! > > During $ESTimation, NONMEM prints PARAMETER values. At iteration 0, these are all 'scaled' to 0.1. During long NONMEM runs I'm sometimes interested in seeing where my current estimate of parameters are, so I would like to re-scale them back. Unfortunately simple re-scalings like "parameter" * 10 * "Initial-estimate" do not work (except for iteration 0 ;-). If I do this for the parameters in the last iteration, I do not end up with the final parameter estimates..?! > > Does anybody know how to re-scale? > > Cheers, Axel > > Here some example: > > initial est.: 0.4715E+00 > initial par.: 0.1000E+00 > final par.: -0.5854E+00 > final est.: 2.38E-01 > > taken from: > > [...] > > 0INITIAL ESTIMATE OF THETA: > LOWER BOUND INITIAL EST UPPER BOUND > 0.0000E+00 0.4715E+00 0.1000E+07 > [...] > > MONITORING OF SEARCH: > > 0ITERATION NO.: 0 OBJECTIVE VALUE: 0.65915E+05 NO. OF FUNC. EVALS.:20 > > CUMULATIVE NO. OF FUNC. EVALS.: 20 > PARAMETER: 0.1000E+00 .. > GRADIENT: 0.1145E+06 ... > > [...] > > 0ITERATION NO.: 61 OBJECTIVE VALUE: -0.39051E+04 NO. OF FUNC. EVALS.:36 > > CUMULATIVE NO. OF FUNC. EVALS.: 2195 > PARAMETER: -0.5854E+00 ... > GRADIENT: 0.3601E+02 ... > 0MINIMIZATION SUCCESSFUL > > [...] > > ************************************************************************************************************************ > > ******************** ******************** ******************** FINAL PARAMETER ESTIMATE ******************** ******************** ******************** > > ************************************************************************************************************************ > > THETA - VECTOR OF FIXED EFFECTS PARAMETERS ********* > > TH 1 ... > > 2.38E-01 ... > > ---------------------------------------------------------------------- > Proprietary or confidential information belonging to Nycomed Group may > be contained in this message. If you are not the addressee indicated > in this message, please do not copy or deliver this message to anyone. > In such case, please destroy this message and notify the sender by > reply e-mail. Please advise the sender immediately if you or your > employer do not consent to Internet e-mail for messages of this kind. > Opinions, conclusions and other information in this message that > pertain to the sender's employer and its products and services > represent the opinion of the sender and do not necessarily represent > or reflect the views and opinions of the employer. > ---------------------------------------------------------------------- > >