And let me for the stats interested that, while a P value can inform the reader whether an effect exists, the P value will not reveal the size of the effect!
"To calculate the p-values Anavex would know the absolute brain loss difference figures, but of course they chose not to reveal - likely because of some secret WGT wonderfulness?"
Exactly it is like these people haven't figured out that small studies have only proven to "not" replicate in larger trials. Hence a few people in Rett to over 70 in rett...now way to fail based of a the first few to a failure in the larger more controlled study. Or great p-values in a P2a to changed goalposts and crappy p-values in the larger yet still undersized p2b study foe AD.