Bioequivalence and Bioavailability Forum

Dear D. Labes!

❝ […] not to round intermediate results.

Well, that’s what I learned too.

❝ May be the whole story is a bit hair-splitting as always with us.

Yes, grumpy old men as usual.

So I will retreat to 0.760 and round everywhere to two decimal places. Until I’ll succeed in convincing Pharsight to modify Phoenix/WinNonlin’s output (which is based on full precision and textual like “Failed to show average bioequivalence for confidence=xx and percent=yy” or “Average bioequivalence shown for confidence=xx and percent=yy”) I’ll have to write an SOP stating ‘Delete the verbatim BE assessment from the output because it might contradict rounded results and provoke questions’.