## S×F vari­­ance [General Sta­tis­tics]

Dear all – or shall I rather say Angus & John?

Since the other thread (due to indenting of posts) becomes increasingly difficult to read I decided to close it. Please continue here.

Regrettably I had too little spare time to dive into. However, some points:
1. #14138: John is correct that the setup should essentially follow FDA’s code for RSABE. Therefore, anything obtained from ABE is not useful.
2. #14141: I developed the RSABE-workflow (see here) in the first place. We presented a poster at the AAPS Meeting in 2013 (download). Ana’s new templates removed the clumsy workaround for joining values of the χ², since chiinv(p, df) was introduced in PHX/WNL6.4 and can be used in the custom transformation (RSABE|Prepare Data for RSABE analysis|s2wr and dfd|Step 4).
@John: Note that these templates will not work in PHX/WNL6.3.
3. #14146: The template is for RSABE, therefore, variability of T is not included (which John cor­rectly pointed out). Yes, it’s doable to add the coding for T.
4. #14147: The template covers the partial replicate as well. Still to do for the next version: A setup for the fully replicated two-sequence three-period (TRT|RTR) design which would avoid the con­ver­gence issues seen in ABE sometimes. BTW, I’ll submit a protocol with such a design to FDA’s OGD next month for review.
5. #14149: Modifying the ABE-part doesn’t do the job (see #1 above). What you could do: Copy the entire Prepare Data for RSABE analysis workflow and change the coding in the second one from R to T. Don’t forget to change all filters and transformations. Then you have both the results for R and T. Proceed from there.

Dif-tor heh smusma 🖖
Helmut Schütz

The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes