Re: Contradictory results from u_test and sign_test

[Rik]

On 07/22/2011 10:04 AM, Alexander Klein wrote:
> Am 15.07.2011 um 22:32 schrieb Rik:
>
>> I think there is an issue here, but it may not be as big as it first
>> appears.  First, sign_test doesn't even run under the development version
>> of Octave because binomial_cdf has been removed.  In general, all of the
>> scripts in statistics/tests have not seen any attention in years and it
>> shows.  I have updated the scripts in statistics/base and am almost done
>> with those in statistics/distributions, but am running out of energy.  If
>> you could do anything to help these functions it would be appreciated.
>>
>> As for your particular question.  I think sign_test is returning not the p 
>> value but (1-p).
> Rik,
>
> that's the one thing I really stumbled upon, since having one function return 
> p and the other 1-p, while passing "<" to both of them comes as a bit of a 
> surprise.
We can change this.  After all, this is the beauty of open source.  So, to
be clear, can you confirm that sign_test is always returning (1-p) where it
should return just p?  If you can confirm this I can make the fix. 
Statistics are not what I do every day though so I don't want to make the
change without a review by someone who knows these things.

--Rik