Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


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

RE: st: testing linear combination of means


From   "Rubil Ivica" <irubil@eizg.hr>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: testing linear combination of means
Date   Thu, 22 Nov 2012 16:15:16 +0100

Thanks, John.




--
Ivica Rubil
Ekonomski institut || The Institute of Economics, Zagreb
Trg J. F. Kennedyja 7, 10 000 Zagreb, Croatia
tel. +385-1-2362-269 || fax. +385-1-2335-165
irubil@eizg.hr || www.eizg.hr


-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of John
Antonakis
Sent: 22. studeni 2012 14:52
To: statalist@hsphsun2.harvard.edu
Subject: Re: st: testing linear combination of means

Hi:

This should be relatively straightforward.

Run this code to give you an idea of what to do:

clear
set seed 123
set obs 1000

*generate y1-y4
foreach var of newlist y1-y4 {
gen `var'= 10 + rnormal()
}

*repeated regressions to estimate intercept (mean)
foreach var of varlist y1-y4 {
reg `var'
est store `var'
}
*combine estimators with suest
suest y1 y2 y3 y4

*the test you are looking for
test 0.5*([y1_mean]_cons - [y2_mean]_cons)  - 0.5*([y3_mean]_cons 
-[y4_mean]_cons) = 0

which in this case gives:

  ( 1)  .5*[y1_mean]_cons - .5*[y2_mean]_cons - .5*[y3_mean]_cons + 
.5*[y4_mean]_cons = 0

            chi2(  1) =    0.01
          Prob > chi2 =    0.9069

HTH,
John.

__________________________________________

Prof. John Antonakis
Faculty of Business and Economics
Department of Organizational Behavior
University of Lausanne
Internef #618
CH-1015 Lausanne-Dorigny
Switzerland
Tel ++41 (0)21 692-3438
Fax ++41 (0)21 692-3305
http://www.hec.unil.ch/people/jantonakis

Associate Editor
The Leadership Quarterly
__________________________________________

On 22.11.2012 14:23, Rubil Ivica wrote:
 > Dear Statalist members:
 >
 > Suppose there are four variables: var1, var2, var3, var4. I need to
test
 > whether
 >
 > 0.5 * [mean(var1) - mean(var2)] - 0.5 * [mean(var3) - mean(var4)]
 >
 > is significantly different from zero.
 >
 > Is there any idea how to perform the test?
 >
 > Thanks in advance,
 > Ivica
 >
 >
 >
 >
 >
 >
 >
 >
 >
 > --
 > Ivica Rubil
 > Ekonomski institut || The Institute of Economics, Zagreb
 > Trg J. F. Kennedyja 7, 10 000 Zagreb, Croatia
 > tel. +385-1-2362-269 || fax. +385-1-2335-165
 > irubil@eizg.hr || www.eizg.hr
 >
 >
 > *
 > *   For searches and help try:
 > *   http://www.stata.com/help.cgi?search
 > *   http://www.stata.com/support/faqs/resources/statalist-faq/
 > *   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index