[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Bug-gsl] Hypergeometric distribution
From: |
Jussi Piitulainen |
Subject: |
Re: [Bug-gsl] Hypergeometric distribution |
Date: |
12 Mar 2004 18:01:05 +0200 |
User-agent: |
Gnus/5.09 (Gnus v5.9.0) Emacs/21.2 |
Brian Gough writes:
> Jussi Piitulainen writes:
>
>> The info page says p(k) = C(n_1,k) C(n_2, t-k) / C(n_1 + n_2,k). It
>> does not tell what the parameters are, but I believe the very last
>> symbol is wrong, and p(k) = C(n_1,k) C(n_2, t-k) / C(n_1 + n_2,t)
>> is meant. It also says the domain of k is
>> max(0,t-n_2),...,max(t,n_1). If "domain" means the possible values,
>> I believe 0,...,min(t,n_1) is better. (No definition is given for
>> C(n_2, t-k) with t < k.) Also, the documentation mentions an N3
>> where T must be meant.
>
> Thanks for the bug report.
> I will correct that in the next release.
I have an embarrassing note to add. The lower bound max(0,t-n_2) in
info is correct and my correction to it was wrong.