# st: RE: Re: obtaining confidence intervals after mfx compute

 From "Jose A. Aleman" <[email protected]> To <[email protected]> Subject st: RE: Re: obtaining confidence intervals after mfx compute Date Mon, 30 Aug 2004 16:13:32 -0400

Thanks very much. The problem is that stdp generates the standard error for
the fitted values of X. This is also commonly referred to as the standard
error of the observation's covariate pattern xjb. In the panel data I'm
using, this error is unique to each observation fitted. The reason I use mfx
compute, however, is because I want to isolate the effect of a discrete
change in one variable on the dependent variable. If I x changes from 4 to
5, and y increases by 20, how do I get the standard error for this
particular change?. Unfortunately, I don't know how to get stata to get
stata to do this for E[y | x].

Jose Aleman
PhD Candidate
Politics Department
130 Corwin Hall
Princeton, NJ 08544
609.937.0190

-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Kit Baum
Sent: Saturday, August 28, 2004 10:17 PM
To: [email protected]
Subject: st: Re: obtaining confidence intervals after mfx compute

Jose said

Does anyone know how to obtain confidence intervals for the estimated Y
variable after the mfx compute command? Let's say you have an estimate
of
your dependent variable, which is what (mfx compute) computing mean
marginal
effects does. A very important issue in using regression estimates is
the
ability to forecast the confidence interval of this dependent variable.
As
far as I can tell, mfx compute gives you a confidence interval for the X
variables, but I need a measure of confidence for the predicted Y
variable.

-whelp regress- indicates that after a regression, you may use
-predict- to calculate either the standard error of prediction (stdp)
or standard error of forecast (stdf). As any econometrics text (or the
Stata manual) will demonstrate, these quantities may be used to
generate an appropriate confidence interval for E[y | x]  or E[y_0 | x_0].

mfx is a very useful tool, but confidence intervals for prediction from
a regression is not what it is for.

Kit

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

• References: