Re: [Gretl-users] Fixed effects forecast
Am 13.08.2011 16:22, schrieb Allin Cottrell:
On Sat, 13 Aug 2011, Leon Unger wrote:
> after investigating further - because the results were quite unsatisfactory -
> I found out that:
>
> 1) there is no memory problem with creating the unit dummies if done via
> 'dummify' (took millisecs for 865 dummies).
> Using 'genr unitdum' even did not succeed when shrinking down the
dataset
> to only include 30 units. I guess there is some bug.
I rechecked the phenomenon: It was due to not *restarting *GRETL after
the memory allocation problem occurred.
With the subsample of 865 units (only trade within OECD) the 'genr
unitdum' works fine, so does 'dummify'!
The whole world trade file contains 33.132 units. Here dummify also
stops after creating some dummies with data error.
Cheers
Leon
> Could you send me the 30-unit dataset, please? I find I can
provoke
> a memory allocation problem with "genr unitdum", but only if the
> dataset contains a huge number of panel units.
>
> Allin
> _______________________________________________
> Gretl-users mailing list
> Gretl-users(a)lists.wfu.edu
> http://lists.wfu.edu/mailman/listinfo/gretl-users
Attachments:
- attachment.html (text/html — 2.1 KB)