For anyone curious about how this would play out in the US, federal courts and most state courts use the Daubert standard. TLDR: experts (including statisticians) can testify if they're using fairly standard methods and there are no significant gaps in the evidence-->analysis-->testimony chain.
http://en.wikipedia.org/wiki/Daubert_standard http://en.wikipedia.org/wiki/Daubert_v._Merrell_Dow_Pharmace...