Re: nancov.m missing

[Jaroslav Hajek]

On Thu, Aug 13, 2009 at 2:53 PM, Søren Hauberg<address@hidden> wrote:
> tor, 13 08 2009 kl. 05:43 -0700, skrev david:
>>    I did not find the function nancov.m in Octave-forge statistics toolbox, 
>> does anyone know where to get this function?
>
> We don't have such a function at the moment, though I think we should.
> The problem is that there are several ways of skipping the NaN's, and
> it's not clear which is the best one.
>
> The attached function circulated on the Octave-Forge list sometime ago.
> It implements two different algorithms. The documentation is not
> complete so you'll have to look at the code to see what it does.
>

I should add that this was this was the ultimate version that skipped
NAs rather than NaNs. A NaN-skipping procedure (i.e. treat all NaNs as
missing data) would be somewhat simpler.


-- 
RNDr. Jaroslav Hajek
computing expert & GNU Octave developer
Aeronautical Research and Test Institute (VZLU)
Prague, Czech Republic
url: www.highegg.matfyz.cz