Thanks for this Bear.  I have a few issues with this line of reasoning.  

First, if I recall your calculations, Phase 2 had a combined 300 patient years dosed on RVX208.  Only half were on Lipitor.  By contrast, Phase 3 has at least 2000 patient year dosed on our drug.  In short, itis quite possible that Phase 2 had a small sample problem.  So RVX may have jumped the gun on assuming that it was Crestor that really did it...when in fact, it could be spurious correlation.

Second, if you are assuming a RRR of 30% for Phase 3, then it is statistically nearly impossible for half the dosed population (on Lipitor) to deliver sub par results on any metric...whether it be a bio marker or an independent risk factor.  

Therefore, I stand by my assumption that Lipitor dosed patients performed in line with Crestor ones.  If that is not the case, then the data simply can't be as good as what DM and Dr Wong are broadly hinting.