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 at the end of May, and its replacement, statalist.org is already up and running.


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

st: SE of linear prediction: Use only SE of slope coefficient(s), or also that of the constant?


From   Jen Zhen <jenzhen99@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: SE of linear prediction: Use only SE of slope coefficient(s), or also that of the constant?
Date   Wed, 1 Dec 2010 13:55:02 +0100

Dear listers,

I have estimated   Y = A + (B1*X1 + B2*X2 + B3*X3) + (C1*Z1 + C2*Z2+C3*Z3)+eps.

The X are a set of mutually exclusive dummies, and the Z are another
set of mutually exclusive dummies.

Now I want to use these estimated coefficients to compute the average
Y for the three different X cases, keeping Z fixed at any one of its
values, for simplicity say when all Z are zero.

I do this simply by computing    A+B1, and similarly for the other
constellations of X.

But I'm unsure what the correct standard error for this is:
Can I simply take the standard error of B1, or do I need also need to
add that of the constant A, as well as the covariance between the
estimated coefficients A and B1?

Many thanks,
JZ
*
*   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