Pooled vs IBD T-R in SAS from non-SASian [Design Issues]

posted by mittyri  – Russia, 2019-03-24 00:13 (2629 d 07:23 ago) – Posting: # 20073
Views: 36,174

Dear Helmut,

❝ A request to the SASians of the forum: Please run Proc MIXED with DDFM=SATTERTHWAITE of the pooled data and both DDFM-options on the data where S is excluded.


Here's my (naive) attempt

<...>
ODS output estimates = _pooled;

proc mixed data=ex631 method=reml ITDETAILS maxiter=200;
class sequence subject period formula carry;
model ln_auc= sequence period formula/ddfm=SATTERTHWAITE outp=out;
random subject(sequence);
estimate 't T-R' formula -1 0 1/cl alpha=0.10;;
run;

Data _pooled;
set _pooled;
pe=round(100*exp(estimate), 0.00001);
lowerCL = lower;
upperCL = upper;
lower=round(100*exp(lowerCL), 0.00001);
upper=round(100*exp(upperCL), 0.00001);
run;

Data noS;
set ex631;
if formula = 'R' | formula = 'T';
run;

ODS output estimates = _TRonly;

proc mixed data=noS method=reml ITDETAILS maxiter=200;
class sequence subject period formula carry;
model ln_auc= sequence period formula/ddfm=SATTERTHWAITE outp=out;
random subject(sequence);
estimate 'T-R' formula -1 1/cl alpha=0.10;;
run;

Data _TRonly;
set _TRonly;
pe=round(100*exp(estimate), 0.00001);
lowerCL = lower;
upperCL = upper;
lower=round(100*exp(lowerCL), 0.00001);
upper=round(100*exp(upperCL), 0.00001);
run;

Results:
Option Label  Estimate StdErr DF tValue Probt Alpha Lower Upper    pe        lowerCL    upperCL
Pooled "t T-R" 0.1497 0.03848 115 3.89 0.0002 0.1  108.97 123.81 116.153  0.0859308889 0.2135523619
IBD     T-R    0.1488 0.03793 56.8 3.92 0.0002 0.1 108.92 123.65 116.047  0.0854035502 0.2122465728
—
Kind regards,
Mittyri

Complete thread:

UA Flag
Activity
 Admin contact
23,653 posts in 4,991 threads, 1,571 registered users;
487 visitors (0 registered, 487 guests [including 26 identified bots]).
Forum time: 08:37 CEST (Europe/Vienna)

I’m all in favor of the democratic principle
that one idiot is as good as one genius, but I draw the line
when someone takes the next step and concludes
that two idiots are better than one genius.    Leo Szilard

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