Re: Beta distribution

[Ben Pfaff]

John Darrington <address@hidden> writes:

> For some reason, the change I'm trying to get ready for check-in
> breaks the test for the beta distribution.

[...]

> Have these numbers been verified at all?  Anyone got any ideas.
> All the other tests are passing.

I verified that most of the values match those output by SPSS.

I'll fix it.  It's probably extreme values causing catastrophic
round-off error.  I'll get rid of the test cases that cause such
extreme values.
-- 
"Mon peu de succès près des femmes est toujours venu de les trop aimer."
--Jean-Jacques Rousseau