[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [patch #5583] NPAR TESTS
From: |
Ben Pfaff |
Subject: |
Re: [patch #5583] NPAR TESTS |
Date: |
Fri, 24 Nov 2006 19:16:08 -0800 |
User-agent: |
Gnus/5.110006 (No Gnus v0.6) Emacs/21.4 (gnu/linux) |
John Darrington <address@hidden> writes:
> On Sat, Nov 25, 2006 at 01:36:39AM +0000, Ben Pfaff wrote:
>
> Follow-up Comment #1, patch #5583 (project pspp):
>
> Have you checked out the algorithms described on spss.com against what
> SPSS
> Statistical Algorithms says? The latter might be dated; who
> knows.
>
> I was actually refering to the pages downloaded from spss.com So far
> as I'm aware, they are identical to those from SPSS Statistical
> Algorithms. I'll check the copy in the UWA library next week to make
> sure.
I have a copy of that book here at home, so I can save you a
trip. Everything on page 8 in npar_tests.pdf from spss.com
(headed "Binomial Tests") is identical to text in SPSS
Statistical Algorithms (2 ed.), except for one point: the .pdf
has a square root in the denominator of the formulas for Z_1 and
Z_2, but the book's formulas omit the square roots.
> In value_dup, I'd prefer to calculate the size as MIN(width,
> sizeof *val).
>
> This would give the wrong answer, since if width is zero, then the
> size should be 8.
Where I wrote MIN, read MAX.
--
Ben Pfaff
email: address@hidden
web: http://benpfaff.org
Re: [patch #5583] NPAR TESTS, John Darrington, 2006/11/24