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

Re: st: Differential effect; regression coefficients

From   Herb Smith <>
Subject   Re: st: Differential effect; regression coefficients
Date   Sat, 15 Aug 2009 07:46:08 -0400 (EDT)

Have a look at


Your constraint is that a1/a4 = a2/a5 = a3/a6 . That is how you are going to find your b coefficient .

On Sat, 15 Aug 2009, Miriam Kuemmel wrote:

Dear readers,

my regression equation looks as follows:

Return = a0 + a1*x1 + a2*x2 + a3*x3 + (b*a1)*x4 + (b*a2)*x5 + (b*a3)*x6.

As you can see the independent variables x1 and x4, x2 and x5, x3 and x6 have the same regression coefficients. Furthermore x4, x5 and x6 have a uniform regression coefficient b.

Is there any possibility to realise this regression in STATA?
Thank you in advance for your help,

Herbert L. Smith
Professor of Sociology
230 McNeil Building
3718 Locust Walk CR
University of Pennsylvania
Philadelphia, PA  19104-6298

215.898.7768 (office)
215.898.2124 (fax)
*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index