Norman,
Have a look at log-likelihood profiling in PsN. LLP documentation is on the
PsN website - I don't think it quite does what you want (it will look for
parameter values that give significant OFV changes rather than changing
parameters by certain proportions).
Best wishes,
Joe
Joseph F St
Dear NMUsers,
University of London School of Pharmacy recently merged with University College
London. Expressions of interest are being sought for senior (Reader/Professor)
researchers to apply for new posts that are being created. I am posting this
on NMUsers in the hope that someone current
Jacob,
I am guilty of having performed such a bootstrap (but didn't do any of the
testing you describe). Anyway, here's an opinion: By using prior in nonmem
you are trying to get an approximation of what the pooled data fit would be and
get an OFV that is theoretically the same as if you did
I have a follow on question - has anyone used L2 with the M3 method for BLQ
handling? Here is my $ERROR code which works fine when I ignore L2:
$ERROR
IPRED = 0
LOQ=LLOQ
IF(ANALY.EQ.1) IPRED=A(3)/VD
IF(ANALY.EQ.2) IPRED=A(4)/VDM
IF(ANALY.EQ.1) SIG=THETA(9)*IPRED
IF(ANALY.EQ.2) SIG=THETA(10)*
Dear Andreas,
When you say you add IIV on dose, I'm not sure exactly what you mean but
suggest you need to take a 2 step approach. In order to replicate variability
in dose, you will need to simulate doses with variability, and then in a second
step use these simulated doses to estimate the Em
Hi Paul,
As I understand it, you don't have data from all trimesters in all subjects
(and anyhow categorising your data like this may not be helpful), so I don't
think it is appropriate to constrain occasions to correspond to trimesters. I
would include an OCC column which increases for every
Nyashadzaishe,
UK and I believe WHO growth charts are derived using LMS method which you can
do in R - look for papers by TJ Cole. I also suspect you might get a response
from a certain NHG Holford telling you to look at his NONMEM method: Paediatr
Anaesth. 2011 Mar;21(3):309-15 - I have only s
Ann
I think your model is starting to be over-parameterised: 4 compartments plus
lag plus transit (have you plotted the individual alag estimates as they have
fairly big omegas?) I think if you cannot describe the data well with a 4 comp
linear model, and are seeing differences in PK with diffe
Desr Ethan,
It is my understanding that you should do an IMP step with EONLY=1 in order to
get an OFV to be used for hypothesis testing after a SAEM step, as the SAEM OFV
cannot be used for likelihood ratio tests. I think your problem is that the
first IMP step has converged (you asked for CTY