Had some of our R people use a (I believe slightly tweaked locally) Statistics::R for some things at one point, but that's still leaving the heavy lifting and coding in R (which of course is just Lisp reimplemented poorly by mathematicians and statisticians</sarcasm mode="slight">). There's also Math::GSL::Statistics which I think I might have installed at one time for said R people to play with but I have only a marginal recollection of that. It's sitting on top of the GNU statistics library so it should be fairly performant but I think it's also going to be lower-level stuff you'd have to build up to the types of things shown in your reference.

This (math heavy statistics) is another of those heavy math areas where like the PDE question recently aren't really in perl's wheelhouse as far as off the shelf solutions go.