Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: st: Panel Data and model specification


From   Jan Bryla <[email protected]>
To   "[email protected]" <[email protected]>
Subject   RE: st: Panel Data and model specification
Date   Mon, 24 Jan 2011 10:37:01 +0100

Dear Maaaa Saaaaaa,
In addition to Chris' comments, you may want to recall that Stata reports two F-statistics when doing -xtreg,fe-. Be sure to interpret the correct one. 


Jan Bryla
The Danish Bankers Association


-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Chris Hajzler
Sent: 21. januar 2011 20:49
To: [email protected]
Subject: Re: st: Panel Data and model specification

Dear Maaaa Saaaaaa,

Members of Statalist typically only offer guidance on Stata-related
questions; I'm not a stata expert myself, but have come to know this
since joining the list, where I occasionally come to ask questions
about Stata when I am unable to find the answer in the help files or
online FAQs. At any rate, I suspect it would be more helpful for you
to consult with a statistics text or other online forum for the types
of questions you have.

I think the proper interpretation of the F-statistic is in fact the
other way around.  Also, including additional independent variables is
not necessary if in fact you think no other measurable variables
influence technological change.  But to the extent that other factors
do, such as education, health, capital, geography, etc, you should
control for these since they might also be correlated with inequality
in some way, in which case the coefficient from the single variable
regression would not be meaningful.

Chris

On Sat, Jan 22, 2011 at 8:13 AM, maaaa saaaaa <[email protected]> wrote:
> Sorry to ask questions which may be obvious to many, but I am just
> starting out with Stata and econometrics so if anyone could help me I
> would really appreciate it.
>
> Basically I need to look at the relationship between inequality and
> technological change, and am using panel data consisting of a measure
> of technological change (technology as a % of GDP) and gini index
> statistics for a sample of countries annually over a 30 year period.
>
> I am only interested in seeing if technological change affects
> inequality so technology is my only dependent variable. When using
> xtreg to run a fixed effects regression my Prob>F value is high so is
> it fair to say that I cant reject the hypothesis that the coefficient
> is 0 and therefore it is likely that technological change does not
> affect growth?
>
> Is it ok that I have not included other variables in the regression? I
> am not really concerned in finding all the factors that influence
> inequality, only in seeing if technology plays any role. So is my
> regression ok as it is?
>
> Also, can anyone give me any idea of whether I should be using logged
> values for my data? I see this done a lot but am unsure when it should
> be used.
>
> Sorry again for the 'newbie' questions, and thank you for any help!
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
>

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index