**Date:** Thu, 24 Oct 2002 14:41:32 -0400
**Reply-To:** Richard Ristow <wrristow@mindspring.com>
**Sender:** "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
**From:** Richard Ristow <wrristow@mindspring.com>
**Subject:** Re: regression models
**In-Reply-To:** <20021024083852.74763.qmail@web40305.mail.yahoo.com>
**Content-Type:** text/plain; charset="us-ascii"; format=flowed
At 01:38 AM 10/24/2002 -0700, Boniface Kalanda<kalanda@liverpool.ac.uk> wrote:

>I have two regression models:
> y= a + bx
> y= c+ dx
>How do i test the hypotheses that
> a is equal to c AND
> b is equal to d
>I would like to do that either through code or menus.

Those two models are structurally identical, so the question makes
sense only if they are estimated on different data (different
variables, or the same quantities measured in different instances, for
x and y).

This is a "homogeneity of regression" problem, then: do the regression
parameters differ in two sets of data?

You need to construct a data set containing both the cases over which
you are estimating the first model and those over which you are
estimating the second, AND a variable I will call "C_MODEL", which is 1
in those cases belonging to the second model and 0 in those cases
belonging to the first.

Then, estimate the model

y = INT + SLOPE*x + INT_DIF*C_MODEL + SLOPE_DF*(C_MODEL*x)

(To do this, you have to compute a variable whose value is C_MODEL*x.)

Then, the test you want is that the two parameters INT_DIF and SLOPE_DF
do *not* contribute significantly to the model.