## ‘dlat’ for 3-period full replicate? [RSABE / ABEL]

❝ I have a problem (both in Phoenix/WinNonlin, R, and – likely – in SAS as well). To calculate *s*_{wR} the FDA wants a linear model (in SAS-lingo

) of repeated reference data with **proc glm***subject* as a factor. However, in a 3-period full replicate they are all in one sequence and the model collapses. Now what?

So the problem is here

`proc glm data=scavbe;`

class seq;

model **dlat=seq**;

ods output overallanova=dglm1;

ods output NObs=dglm3;

title1 'scaled average BE';

run;

I would look at the original formula

\(s_\text{wR}^2=\Large\frac{\sum\limits_{i=1}^{m}\sum_\limits{j=1}^{n_i}\left(D_{ij}-\overline{D}_{i\,\cdot}\right)^2}{2\left(n-m\right)}\)

So it is impossible to get D for `TRT` sequence. Could we just omit one sequence here?Kind regards,

Mittyri

### Complete thread:

- any SAS or R-macro for 3 period two sequence RSABEIs Achievwin 2023-07-05 18:38 [RSABE / ABEL]
- Use the one for TRTR | RTRT Helmut 2023-07-06 08:46
- RSABE R coded by Detlew mittyri 2023-07-06 14:07
- ‘dlat’ for 3-period full replicate? Helmut 2023-07-07 14:41
- ‘dlat’ for 3-period full replicate?mittyri 2023-07-07 16:04
- Likely wrong workaround? Helmut 2023-07-07 20:06
- a bit corrected workaround mittyri 2023-07-07 22:52
- THX! Another attempt… Helmut 2023-07-08 12:15
- complete.cases for dlat and ilat? mittyri 2023-07-09 21:45

- a bit corrected workaround Achievwin 2023-07-10 20:43

- THX! Another attempt… Helmut 2023-07-08 12:15

- a bit corrected workaround mittyri 2023-07-07 22:52

- Likely wrong workaround? Helmut 2023-07-07 20:06

- ‘dlat’ for 3-period full replicate?mittyri 2023-07-07 16:04

- ‘dlat’ for 3-period full replicate? Helmut 2023-07-07 14:41

- RSABE R coded by Detlew mittyri 2023-07-06 14:07

- Use the one for TRTR | RTRT Helmut 2023-07-06 08:46