st: Comparing "almost similar" variables across regression equations

["Christer Thrane" <ch-thran@online.no>]

Hi,

I have three regression models with the same dependent variable, i.e.

Y = a + b1x + control variables
Y = a + b2y + control variables
Y = a + b3z + control variables

where Y is the demand for a product type (i.e. money spent), x, y, and z are 
product quality ratings from three different raters (on a scale from 1 to 5) 
and the controls are a number of objectice product attributes.

I want to examine if the effects of x, y, and z are statistically different 
from each other. Since the ratings are highly correlated, I cannot include 
them in the same regression and use the test command.

Can this be done? If so, how?

Any help is appriciated!

Christer Thrane
Lillehammer University College 

*
*   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/