2 replies to this topic

[tsang0323]

We conducted a replicate study which is RRT, RTR and TRR. We completed 90%CI with default setting, such as attachments. However, the study was completed with 5 groups, so that I want to know how group effect is analyzed. I have searched BABE forum for couple of days. but still can not get the answer. Would anyone please guide me how to do it in the WLN? thank you.

 

I have seen a paper use: Group+Sequence+Period+Treatment+Random errors where Random errors is Random within and between subject errors. However, what about Formulation*Group such in the 2x2 crossover study? I am not so sure it is correct.

 

 

Charlie

Attached Thumbnails

• 
• 
• 

Edited by tsang0323, 13 April 2016 - 01:46 AM.

[tsang0323]

Dear All:

 

Due to cannot find out the answer for group effet in the replicated study, we are considering to use following SAS code to analysis the 2x3x3 replicated study with 5 groups

 

proc mixed data=mydata;
class Seq Subject Period Drug batch;
model ln_AUC0_t= Group Sequence  Period(Group) Subject(Sequence*Group) Formulation Formulation*Group/ ddfm=satterth;
random Drug/type=FA0(2) sub=Subject G;
repeated/grp=Drug  sub=Subject;
estimate 'test-ref' Drug  -1 1/ CL alpha=0.10;
title 'lnAUC0-t' ;
ods output Estimates=out1;
run;

 

We have modified the default setting of Phoenix WinNonlin and put "Group Sequence  Period(Group)  Formulation Formulation*Group" as fixed effects, however, we can not figure out how to deal with "Subject(Sequence*Group)" effect. In default setting, a random terms for Formulation*Subject is already existing, therefore, we added another random effect for Subject(Sequence*Group), but result shows same as before the effect was added. Does it mean that the effect we do not condider in the model?  

[mittyright]

Dear Tsang,

 

it is very strange that you didn't find the model in BEBAC.

Citing the Guru:

• Group model I:
• fixed:  Group+Sequence+Sequence(Group)+Period(Group)+Treatment+Treatment×Group
  random: Subject(Sequence×Group)
  If the Treatment-by-Group term is not significant (p ≥0.1) this term can be dropped from the model, proceeding to Group Model II.
  If the Treatment-by-Group term is significant (p <0.1), FDA’s Division of Bioequivalence requests that equiva­lence be demonstrated in one of the groups, provided that the group meets minimum requirements for a com­plete BE study (i.e., 12).
• Group model II:
  fixed:  Group+Sequence+Sequence(Group)+Period(Group)+Treatment
  random: Subject(Sequence×Group)