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: Trends and Time dummies


From   Maarten Buis <maartenlbuis@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Trends and Time dummies
Date   Mon, 12 Sep 2011 16:13:48 +0200

--- "Venkiteshwaran, Vinod" wrote:
> I noticed that in the first regression ' reg degree i.year c.coh' , coh is automatically dropped due to multicollinearity.
> Therefore  Yhat1 and Yhat2 are necessarily the same!

If you type -reg degree c.coh i.year- instead, one of the dummies get
dropped, and still nothing changes. The fact that all this does not
matter is a logical consequence of what I said earlier: These models
are exactly the same in the sense that they just redistribute the same
information across different coefficients.

Than why does it appear to matter whether I entered -c.coh i.year- or
-i.year c.coh-? With perfect colinearity it does not matter which
variable is dropped, all models lead to the same predictions. So Stata
has no "statistical reason" for dropping one variable rather than the
other. So Stata uses the only other information available and that is
the order in which the variables are entered in the model.

Hope this helps,
Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany


http://www.maartenbuis.nl
--------------------------
*
*   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