Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: RE: Areg, absorb
Nick Cox <firstname.lastname@example.org>
Re: st: RE: Areg, absorb
Mon, 11 Apr 2011 14:52:41 +0100
So identifier is "country1 country2" and time variable "year"? Well,
then -group(country1 country2 year)- will define a distinct (and
unique) value for each observation, which is far too many dummies.
On Mon, Apr 11, 2011 at 2:48 PM, emanuele mazzini
> Exactly country1 country2 and year.
> 2011/4/11 Nick Cox <email@example.com>:
>> Everything depends on whether you want dummies for _combinations_ of
>> -country1-, -country2- and -year-.
>> What precisely defines a panel?
>> On Mon, Apr 11, 2011 at 1:30 PM, emanuele mazzini
>> <firstname.lastname@example.org> wrote:
>>> I tried that but doesn't really work. Curiously, Stata reports
>>> insufficient observations. That's kind of strange, however.
>>> 2011/4/11 Jan Bryla <JBR@finansraadet.dk>:
>>>> Would it not be possible for you to first generate group id's based on country1 country2 and year, and then use -areg- to control for each group? I think that would capture the desired effects.
>>>> In that case it would be something like:
>>>> Egen id=group(country1 country2 year)
>>>> Areg ..., abs(id)
>>>> /Jan Bryla
>>>> -----Original Message-----
>>>> From: email@example.com [mailto:firstname.lastname@example.org] On Behalf Of emanuele mazzini
>>>> Sent: 11. april 2011 13:33
>>>> To: email@example.com
>>>> Subject: st: Areg, absorb
>>>> Dear all Stata users,
>>>> I am trying to work out a regression with panel data in which I have
>>>> to control for country1, country2 and year.
>>>> I tried to ran a regression after creating a dummy for all three of
>>>> them and obviously in the result Stata reports the estimates of all
>>>> the dummies I created which I do not want to show in the output of the
>>>> regression. I tried to get the same result with the command: areg...,
>>>> absorb(varname) but the point is that areg does not allow me to
>>>> include more than one variable, and in this case I would need three.
>>>> Hence, my brief question is: is there a way to include in the
>>>> regression the fixed effects for country1, country2 and year without
>>>> Stata showing all the coefficients of the dummies I create?
* For searches and help try: