This is the mail archive of the
gsl-discuss@sources.redhat.com
mailing list for the GSL project.
Re: Geometric distribution
- From: Brian Gough <bjg at network-theory dot co dot uk>
- To: Giulio Bottazzi <giulio dot bottazzi at libero dot it>
- Cc: gsl-discuss at sources dot redhat dot com
- Date: Thu, 4 Nov 2004 17:52:33 +0000
- Subject: Re: Geometric distribution
- References: <20041030121252.7a0f9d7c.giulio.bottazzi@libero.it>
Giulio Bottazzi writes:
> I've a simple question: why the geometric distribution, inside GSL, is
> defined according to
> prob(k) = p (1 - p)^(k-1) for k = 1, 2, 3, ...
> rather than the more canonical
> prob(k) = p (1-p)^k for k = 0, 1, 2, ...
> is there some deep reason I'm missing?
I don't think so, it's just the convention from Knuth.
--
Brian Gough
Network Theory Ltd,
Commercial support for GSL --- http://www.network-theory.co.uk/gsl/