Bioequivalence and Bioavailability Forum

Dear All,

I searched this forum and saw much topics about SAS PROC Mixed as shown in FDA Bioequivalence Standards 2014.

The following illustrates an example of program statements to run the average BE
analysis using PROC MIXED in SAS version 9.3, with SEQ, SUBJ, PER, and TRT
identifying sequence, subject, period, and treatment variables, respectively, and
Y denoting the response measure [e.g., log(AUC) and log(Cmax)] being analyzed:

PROC MIXED data=   ;
CLASS SEQ SUBJ PER TRT;
MODEL Y = SEQ PER TRT/ DDFM=SATTERTH;
RANDOM TRT/TYPE=FA0(2) SUB=SUBJ G;
REPEATED/GRP=TRT SUB=SUBJ;
ESTIMATE 'T vs. R' TRT 1 -1/CL ALPHA=0.1;
run;

I can't understand why TRT was included in RANDOM effect. TRT represents treatment group, which is are usually two groups. The researhers only consider that two groups, so I think TRT should be fixed effect variable.

In my perspective, SEQ should be included in random effect.

Please help to give some explanation.

Thanks.