WinNonlin is lack of precision or? [Software]

posted by Helmut Homepage – Vienna, Austria, 2011-11-06 15:46 (5333 d 03:45 ago) – Posting: # 7621
Views: 13,537

Dear yicaoting!

❝ But you as everyone know (as WNL's usr guide pointed, Phoenix WinNonlin 6.0 guide Page 338), to convert

90% CI of LSMean(R-T) to 90% CI of GeoMean Ratio(%) (T/R), we only need a simple calculation like

CI_Lower = 100 · exp(lower)

CI_Upper = 100 · exp(upper)

❝ No iteration is needed, and no optimization algorithm is needed.


See my other post. No optimization here, but lower and upper are obtained by REML (as ElMaestro pointed out). Default settings in PHX/WNL are maximum 50 iterations, estimability tolerance 10-5, singularity tolerance 10-10, convergence criterion 10-10. BTW, with our dataset convergence is reached in the first iteration [-2×REML log(likelihood) 4.8289659].

Dif-tor heh smusma 🖖🏼 Довге життя Україна! [image]
Helmut Schütz
[image]

The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes

Complete thread:

UA Flag
Activity
 Admin contact
23,653 posts in 4,991 threads, 1,570 registered users;
104 visitors (0 registered, 104 guests [including 25 identified bots]).
Forum time: 20:31 CEST (Europe/Vienna)

To propose that poor design can be corrected by subtle analysis techniques
is contrary to good scientific thinking.    Stuart J. Pocock

The Bioequivalence and Bioavailability Forum is hosted by
BEBAC Ing. Helmut Schütz
HTML5