[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: comparing three gorups

From   "Rajesh Tharyan" <>
To   <>
Subject   RE: st: comparing three gorups
Date   Sun, 7 Sep 2008 09:49:34 +0100

Hi maarten,

Thanks very much.. that is very helpful. One of the variables is highly non
normal but log transformation makes it reasonably close to normal. So I
suppose I could do that.
In the example you have created three groups based on rep78. A mvreg is run
with mpg and trunk as the depvars with dummies for the three groups of

The output shows that w.r.t mpg group 4 is more similar to group 3. w.r.t
truck again group 4 is more similar to group 3. The parmest gives me an
overall F. But how I do I interpret that w.r.t to mpg and trunk combines gp
4 is more similar to go 3.


-----Original Message-----
[] On Behalf Of Maarten buis
Sent: 07 September 2008 08:03
Subject: Re: st: comparing three gorups

--- Rajesh Tharyan <> wrote:
> I have 3 groups of companies, each group characterised by 2 variables
> x and y, say groups A, B and c. What is the simplest way to test
> whether A is similar to B or C in terms of these two variables? 

The example below will work when x and y are, conditional on your
grouping variable, approximately normally distributed.

*---------- begin example ----------
sysuse auto, clear
recode rep78 1/2=3
xi: mvreg mpg trunk = i.rep78
testparm _I*
*----------- end example -----------

Hope this helps,

Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands

visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434

+31 20 5986715

*   For searches and help try:

*   For searches and help try:

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