As i said in my message, I wanted to know if by imposing equality between coef I can get test results equivalent to the ones obtained with a chow test (for 2 categories). Probably the name is no more chow, but it has the same meaning of this test. the only difference is related to the no of cateories employed.
Anyway thanks, I'm going to add this question:
is the tes result enough to allow me to run separate reg (one for each category)??
thanks
-----Messaggio originale-----
Da: [email protected] per conto di Richard Williams
Inviato: lun 03/03/2008 15.19
A: [email protected]; [email protected]
Cc:
Oggetto: Re: st: chow test for more than 2 coef
At 08:47 AM 3/3/2008, Mussida Chiara wrote:
>Hi Guys!
>I'm thinking about the logic and the proper way to run a chow test
>(or a simple test for the coef equality) for more than 2 covariates.
>More precisely these are 5.
>If I say stata after the reg output: b1=b2=b3=b4=b5, does it perform
>my desired test?I guess...
>thanks a lot,
>chiara
Unless Chow test has some broader meaning I am not aware of, this is
not a chow test. Chow tests are done when you compare the equality
of coefficients for 2 or more different groups. But yes, if you just
want to test whether coefficients are equal, you can give a command like
testparm x1 x2 x3 x4 x5, equal
or else
test x1 = x2 = x3 = x4 = x5
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: [email protected]
WWW: http://www.nd.edu/~rwilliam
*
* 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/
<<winmail.dat>>