Speed improvement [R for BE/BA]

» I believe this implies that matrix inversion is done in a clever fashion in R's solve function; as you pointed out PharmCat inversion can be slow (and unstable) as matrices get large, but perhaps the LAPACK routine used by R reduces the task intelligently, possibly through some of the same tricks described for e.g. the Alglib routines..

It is very good question to explore. If we suppose that some routine knows something about structure it should make big work to recognize block-diagonal or/and symmetric matrix structure.

I think, main cause is a overhead for each function call. Another problem - many intermediate products for %*%