## Braveheart! [R for BE/BA]

Hi ElMaestro,

» it is rather experimental.

» […] which means we have:
» A variance for T (combined within and between)
» A variance for within-R
» A variance for between-R

Correct. Will be interesting what you get because $$\sigma_{wT}^2+\sigma_{bT}^2$$:
0.04367 (Phoenix) and 0.03771 (SAS).

» Hessian, positive definite, etc.. all this comes down to the details of SAS's or WinNonlin's optimiser. I am playing around with optim in R (BFGS, L-BFGS-B bounded, and Nelder-Mead) and with one of my own making.

If you succeed, the community will love you. Might win you the Fields medal.

As long as a genius (you?) is not able to come up with a solution working in all cases, I can only repeat:

Avoid partial replicate designs!

It might not be possible to evaluate the study for ABE (though RSABE works in any case).

Dif-tor heh smusma 🖖
Helmut Schütz

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