Bioequivalence and Bioavailability Forum • Potvin – all effects fixed (PHX/WNL vs. SAS, R)

Potvin – all effects fixed (PHX/WNL vs. SAS, R) [Two-Stage / GS Designs]

posted by Helmut – Vienna, Austria, 2012-10-26 21:35 (4977 d 05:27 ago) – Posting: # 9462
Views: 15,799

Dear all,

Jiří Hofmann brought one subtlety to my attention. I set up the pooled analysis with Sequence + Stage + Period(Stage) + Treatment [fixed] and Subject(Sequence × Stage) [random].

For Example 2 I got:

User-Specified Confidence Level for CI's and Power = 94.1200

Reference: R   LSMean= 1.133431  SE= 0.171385  GeoLSM= 3.106297

---------------------------------------------------------------

Test:      T   LSMean= 1.147870  SE= 0.171385  GeoLSM= 3.151473



    Ratio(%Ref) = 101.4544



     CI User = ( 88.4452,  116.3770)



    Average bioequivalence shown for confidence=94.12 and percent=20.0.

When we specified all effects fixed (EMA?), Phoenix/WinNonlin (tested 6.2.51, 6.3beta, 6.3) spits out:
ERROR 11050: Parsing error: The containing term must be in the model.

OK, since in PHX/WNL the BE-module sits on top of the LME-engine I set up the model directly in LME. Could reproduce the mixed model:

Least squares means

Treatment  Estimate  StdError Denom_DF T_stat P_value Conf T_crit Lower_CI Upper_CI

-----------------------------------------------------------------------------------

        R   1.13343  0.171385  18.4   6.61338  0.0000   95  2.098   0.7739    1.493

        T   1.14787  0.171385  18.4   6.69763  0.0000   95  2.098   0.7883    1.507



Estimate Statements

Title   Estimate  StdError  Denom_DF   T_stat P_value Conf T_crit Lower_CI Upper_CI

-----------------------------------------------------------------------------------

T – R  0.0144389  0.0677463    17    0.213132  0.8338 94.12 2.026  -0.1228   0.1517

… giving back-transformed 101.4544 (88.4452, 116.3770), identical to BE-wizard’s results.

I get the same values in the all-fixed model – but could not request LSMeans any more; otherwise I got the same error like in the BE-wizard. Though we don’t need these values in the BE assessment I would be interested how other software deals with it (SAS, R?).

—
Dif-tor heh smusma 🖖🏼 Довге життя Україна!
Helmut Schütz

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

Complete thread:

Potvin – all effects fixed (PHX/WNL vs. SAS, R)Helmut 2012-10-26 19:35 [Two-Stage / GS Designs]
- Potvin – all effects fixed (PHX/WNL vs. SAS, R) ElMaestro 2012-10-26 20:14
  - Potvin – all effects fixed (PHX/WNL vs. SAS, R) Helmut 2012-10-26 20:25
    - Potvin – all effects fixed (PHX/WNL vs. SAS, R) ElMaestro 2012-10-26 22:05
- Potvin – all effects fixed - SAS d_labes 2012-10-29 09:57
  - Potvin – all effects fixed (PHX/WNL resolved) Helmut 2012-11-06 01:43
    - Potvin – all effects fixed (PHX/WNL resolved) ElMaestro 2012-11-06 11:48
      - Potvin – all effects fixed (PHX/WNL resolved) Helmut 2012-11-06 13:48
        
        Mysterious ways ElMaestro 2012-11-06 15:27
        
        Mysterious ways Helmut 2012-11-06 17:06