Statalist


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

Re: st: Comparing coefficients between two samples


From   John Antonakis <John.Antonakis@unil.ch>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Comparing coefficients between two samples
Date   Mon, 30 Mar 2009 20:42:28 +0200

I don't think it would be a problem if your equation is overidentified. If you are worried about having an endogenous dummy, that should not be a problem either. Check out the paper by Angrist:

http://ideas.repec.org/p/nbr/nberte/0248.html

Perhaps others have ideas.

Best,
J.

____________________________________________________

Prof. John Antonakis
Associate Dean Faculty of Business and Economics
University of Lausanne
Internef #618
CH-1015 Lausanne-Dorigny
Switzerland

Tel ++41 (0)21 692-3438
Fax ++41 (0)21 692-3305

e-mail: john.antonakis@unil.ch

____________________________________________________



On 30.03.2009 20:26, Erasmo Giambona wrote:
Dear John,

Thanks very much for your suggestion. I wonder whether this would
still be fine when the variable of interest is the endogenous
variable.

Regards,

Erasmo

On Mon, Mar 30, 2009 at 6:32 PM, JOHN ANTONAKIS <john.antonakis@unil.ch> wrote:
Hi Erasmo:

One solution may be to create an indicator variable (for the groups) that
you interact with your variables of interest?  A significant interaction
indicates that the coefficients are not the same across the two groups.

HTH,
John.

____________________________________________________

Prof. John Antonakis
Associate Dean Faculty of Business and Economics
University of Lausanne
Internef #618
CH-1015 Lausanne-Dorigny
Switzerland

Tel ++41 (0)21 692-3438
Fax ++41 (0)21 692-3305

____________________________________________________



On 30.03.2009 17:06, Erasmo Giambona wrote:
Dear Statalist,

I am fitting the same exact model to two different samples using
xtivreg2. I would like to test whether the coefficients on the
endogenous variables are statistically different from each other
across the two groups.

I understand that this test can be performed with suest after regress,
but suest does not work after xtivreg2.

I would appreciate any suggestions on how I could perform this test in
this case.

Regards,

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



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