Bookmark and Share

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: first-difference regression


From   Christopher Baum <kit.baum@bc.edu>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   Re: st: first-difference regression
Date   Wed, 28 Sep 2011 04:02:20 -0400

<>
On Sep 28, 2011, at 2:33 AM, donsaane wrote:

> When you run a first- difference method, do you always
> put : noconstant ?  For example : reg dx dy, noconstant, or
> you just run it like OLS . eg : reg dx dy
> Because I read an article and they put «noconstant» , so I
> want to know if when we run a first difference, we always put «noconstant»

If you write down a linear model in levels and take first differences, the constant disappears.
If one of the regressors is a time trend, its difference is constant, and your FD regression will have a constant term.
If you do not believe there should be a trend in the level equation, then you should not use a constant in the FD equation.

Kit

Kit Baum   |   Boston College Economics & DIW Berlin   |   http://ideas.repec.org/e/pba1.html
                              An Introduction to Stata Programming  |   http://www.stata-press.com/books/isp.html
   An Introduction to Modern Econometrics Using Stata  |   http://www.stata-press.com/books/imeus.html




*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index