[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: re: missing dummy variable

From   "Wallace, John" <>
To   <>
Subject   st: RE: re: missing dummy variable
Date   Wed, 10 Oct 2007 13:30:14 -0700

Agreed - although I have occasions in the data I work with where the
grand mean itself is of interest, and the variation of the coefficients
from that mean is useful (hence my interest in -xi3- ).  The problem is
the missing coefficient for one of the indicators.  

-----Original Message-----
[] On Behalf Of Kit Baum
Sent: Wednesday, October 10, 2007 11:51 AM
Subject: st: re: missing dummy variable

John said

reg mpg foreign domestic, noconst hascons
xi3: regress mpg e.foreign
xi3: regress mpg e.make
*------------------ end example ---------------

Its clear that the information in the first two regressions is
equivalent, but the display would be better still if it was a
combination of both!  If the _cons from the second regression was
combined with the explicit listing of both indicators in the first.

When the list of indicator variables gets long (as in the third
regression) , and especially when there are interactions,  the task of
interpreting the dropped variables (and especially significance in the
t-test relative to the grand mean) becomes non-trivial (to me at least).

For the regression on make,

xi: reg mpg i.make

will produce a constant term which _is_ the coefficient on the  
omitted make.
Note that xi3 DOES NOT do that! Its constant term is the grand mean,  
and it is a pain in the rear to compute the missing coefficient from  
that (it is the constant minus the sum of all the others, but - 
lincom- doesn't do wildcards). I don't think -xi3- is at all helpful  
in this regard.


Kit Baum, Boston College Economics and DIW Berlin
An Introduction to Modern Econometrics Using Stata:

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index