st: stupid heteroskedastic question

[Kit Baum <kitbaum@mac.com>]

(That was the original poster's title!)

Benn said

Say I want to do the basic fix for heteroskedasticity
in the linear model

Y = b0 +b1X1 + b2X2 + noise

by dividing through by 1/X1.

How do people report the results ? Do they
report the new coefficients, or transform back
to the old coefficients ?



Don't do this "by hand". Use weights in the estimation. help weights  
(and [U] weight, weighted estimation) for the details. Everything  
then is in the context of the original variables (R^2, RMSE, etc.)

Kit Baum, Boston College Economics
http://ideas.repec.org/e/pba1.html


*
*   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/