I'm assuming they didn't stratify with respect to all possible variables.
If a baseline variable is deemed consequential to the outcome of a pivotal trial, the sponsor has two options: i) stratify the arms according to this variable; or ii) make the primary endpoint a (pre-specified) Cox regression analysis that includes the variable in question. In the BRAVO trial, Teva did neither of the above, and therein lies the problem.
Based on today’s share price, investors evidently didn’t buy the doublespeak in Teva’s PR.
“The efficient-market hypothesis may be the foremost piece of B.S. ever promulgated in any area of human knowledge!”