Getting variance components [🇷 for BE/BA]

posted by StatR – Turkey, 2017-02-08 09:41 (2605 d 03:23 ago) – Posting: # 17033
Views: 17,479

Hi again d_labes,

I tried to find the correct model by the post you referred.

❝ In the older package nlme / lme() you may formulate the model similar to the FDA code. See that post.


Unfortunately, I am confused after reading tons of post, and I could not figure out what is "trt", "tmt" ... Simply, my data is as follows

 Subject Formula Period Sequence     Yijk
       1       1      1        1 4.933014
       1       0      2        1 5.006829
       1       1      3        1 4.854162
       1       0      4        1 5.081755
       2       1      1        1 4.854738
       2       0      2        1 4.690311


Where Yijk is the PK characteristic. The first sequence represents "TRTR" and the second sequence: "RTRT". In the formula 1 = T and 0 = R. In the referred post you say that

model2 <- lme(y~ drug + prd + seq,
# this random statement fits a symmetric positive definite covariance matrix,
# identical to UN in SAS???
                random= ~ tmt-1|subj,
                #different within variabilities                 
                weights=varIdent(form = ~ 1 | drug),
                data=BlaBla, method="REML")


In your model y = Yijk, drug=Formula, prd=Period, seq=Sequence,
but what is tmt? Also, is the my data format correct for the lme? Or, Should I change Formula as 1 = T, 2 = R and Sequence as 1 = TRTR, 2 = RTRT? Could you please make me clear.

Best.

Complete thread:

UA Flag
Activity
 Admin contact
22,957 posts in 4,819 threads, 1,639 registered users;
72 visitors (0 registered, 72 guests [including 5 identified bots]).
Forum time: 13:04 CET (Europe/Vienna)

Nothing shows a lack of mathematical education more
than an overly precise calculation.    Carl Friedrich Gauß

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