From: Joern Loetsch
Subject: censored data
Date: Sunday, January 13, 2002 4:08PM
Dear nonem users,
how does one fit censored data. I.e., when the "true" value could be greater than
(some of) the measured one because the measuring device had been at its upper limit.
Thanx in advance
J. Lotsch
______________________________________________________
Jorn Lotsch, MD
pharmazentrum frankfurt, Dept. of Clinical Pharmacology
Johann Wolfgang Goethe-University Hospital
Theodor-Stern-Kai 7
D-60590 Frankfurt am Main
GERMANY
Tel.:+49-69-6301-4589
Fax.:+49-69-6301-7636
censored data
From: Lewis B Sheiner
Subject: censored data
Date:Sun, 13 Jan 2002 10:51:55 -0800
Here are three papers that are relevant ... All use one or more methods to deal with
censoring, although in none of the papers except #1 is that the primary focus.
1. Beal, S.L., Ways to fit a pharmacokinetic model with some data below the
quantification limit. Journal of Pharmacokinetics and Biopharmaceutics, 2001.
28(5): p. 481-504.
2. Luks, A.M., et al., Opioid-induced analgesia in neonatal dogs: pharmacodynamic
differences between morphine and fentanyl. Journal of Pharmacology and Expertimental
Therapeutics, 1998. 284: p. 136-141.
3. Lu, J., et al., Selecting reliable pharmacokinetic data for explanatory
analyses of clinical trials in the presence of noncompliance. Journal of
Pharmacokinetics and Pharmacodynamics, 2001. 28(4): p. 343-362.
--
_/ _/ _/_/ _/_/_/ _/_/_/ Lewis B Sheiner, MD (lewis@c255.ucsf.edu)
_/ _/ _/ _/_ _/_/ Professor: Lab. Med., Biophmct. Sci., Med.
_/ _/ _/ _/ _/ Box 0626, UCSF, SF, CA, 94143-0626
_/_/ _/_/ _/_/_/ _/ 415-476-1965 (v), 415-476-2796 (fax)
From: Leonid Gibiansky
Subject: censored data
Date:Mon, 14 Jan 2002 07:25:54 -0500
I have not tried it, but one option may be to model censoring within the ERROR block, e.g.,
$ERROR
IPRED=F*EXP(EPS(1) )+EPS(2)
IF(IPRED.GT.LIMIT) IPRED=LIMIT
Y=IPRED
Leonid