Bioequivalence and Bioavailability Forum

Hi yuvrajkatkar

❝ I am not getting why we used geometric least square means instead of mean in BA/BE studies.

We are working with logarithmic tranforms of the Cmax- and AUC-values, and we have a keen interest in the means of those. However, once we backtransform the mean of the logged values we end up with a quantity that can be thought of as the geometric mean.

Example (somewhat simplified):
Consider these three AUCs for Test: 10.1, 12.4, 11.4
And for Ref                       : 11.5, 11.6, 13.2

Log means are logT=2.42 and logR=2.49 (natural logs here, but 10-based can be used too). The difference between the two is: log(T)-log(R)=-0.0699.
But hey, the grumpy old math teacher with bad breath in hi-school tought us that we can write that as log(T/R)=-0.0699, so we backtransform this and get T/R=0.932.

Now try and check the geometric means of T and R (untransformed). They are 11.26 and 12.08. If you take their ratio you find that the Geometric mean ratio is 0.932 just as we got above. I personally never think of geometric mean ratios; it is confusing to me. I think of them as backtransformed mean-log ratios.

Hope this makes sense.

Best regards
EM.