Re: [Gretl-devel] our handling of daily data
Am 05.06.2014 01:57, schrieb Allin Cottrell:
On Wed, 4 Jun 2014, Sven Schreiber wrote:
> Am 26.05.2014 21:07, schrieb Allin Cottrell:
>> Sven has raised the question of the handling of daily data in gretl;
>> see the threads starting from
>>
>> http://lists.wfu.edu/pipermail/gretl-users/2014-May/010037.html
>>
>> I'm glad of that: it's time we clarified what we do now, and what we
>> should do in future. (But please note, I'm mostly talking here about
>> 5-day financial-market data; other sorts of daily data might require
>> different handling.)
>
> Just to check: With my example datasets I couldn't figure out whether
> this also applies to hourly data -- for example missing data during the
> night or also weekends.
OMG!! Now it's gappy hourly data!
Well, OK, to be a bit less ditzy, if data of this sort pose a real
issue for users then I'll be willing to think about it, but I'm not
going to take the initiative on something that is beyond my ken.
Personally I have next-to-zero need for it, I worked with an hourly
dataset once in my life I think and there it just worked (in gretl) as
far as I remember. However, I think I also had chosen that dataset
partly because there were no gaps.
It just occurred to me that the gaps issue is more or less the same for
data with a higher frequency than daily because missing days obviously
propagate to the sub-periods. And since that got fixed in gretl now I
wondered whether the by-minute data stuff has been handled as well.
I guess the broader point is whether gretl aims to be a tool for
empirical finance people. If that's the case, then stuff like this
probably should be handled. If not, well then resources shouldn't be
spent there.
cheers,
sven