KS routines

[Brian Gough]

Robert G. Brown writes:
 > Is there any interest in my contributing the KS stuff I wrote back to
 > the GSL?  If so should I just submit the code (it is pretty simple) or
 > try to wrap it up GSL style first?  The two routines are the simplest KS
 > test -- compare a vector of e.g. p-values or other presumably uniform
 > random deviants to a truly uniform distribution and produce a p-value
 > that the one came from the other.  It would be fairly straightforward to
 > add a routine that compared a vector of samples from two distributions
 > to see what the probability is they could (not) be drawn from the same
 > distribution, as well, although I haven't written it yet.

We don't have any statistical tests.  The algorithms for the tests
themselves are usually straightforward, it's mainly a question of
designing a nice api and naming convention that can handle everything
in a coherent way.

-- 
Brian Gough

Network Theory Ltd,
Publishing Free Software Manuals --- http://www.network-theory.co.uk/