Bioequivalence and Bioavailability Forum

Hi sudy,

next time you upload a PNG please 640px (longest side) or better only the numbers. I had a hard time to read the results.

❝ Why Inter subject CV is not calculated for Cmax?

Unless you want to deal with imaginary numbers, the square root of a negative value is not defined. Since ℯ^{(MSs – MSe)/2} = 0.994155, √–0.005845 don’t work.

❝ Is this formula is correct to calculate between subject variability on log transformed data for two way cross over study?

Yes. See there.

❝ If i calculate manually in excel, I am getting the value around 28% for cmax. But SAS gives error.

Please check what you have done in Excel. Cannot work:

A1 0.06596695
B1 0.07769188
C1 =(A1-B1)/2
D1 =EXP(C1)
E1 =D1-1
F1 =100*SQRT(E1)

What do you get? 28% is CV_intra – in Excel-lingo 100*SQRT((EXP(B1)-1)).

❝ One more point i have noted that, the MSS is very low by SAS, but manually this value is very high.

No idea. I don’t have a crystal ball which could tell me what you are doing “manually”.

❝ Why R-square is very low for Cmax?

Higher variability than the ones of AUCs ⇒ lower R². As expected.