Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

Re: st: SUR system - Compare intercepts from several regression


From   John Antonakis <John.Antonakis@unil.ch>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: SUR system - Compare intercepts from several regression
Date   Tue, 29 Oct 2013 21:03:04 +0100

To see what the coefficient is named, after running an estimation command like regress or suest type:

"command", coefleg

Try:
sysuse auto
reg price mpg
est store mpg
reg price weight
est store weight
suest mpg weight
suest, coefleg
test  _b[mpg_mean:_cons] = _b[weight_mean:_cons]

suest uses the all data available for the particular model. sureg uses all data available across models.

If you have lots of missing data then read-up on the command -sem- with -method(mlmv). You will do all you want to do with the -sem- command too.

HTH,
J.

__________________________________________

John Antonakis
Professor of Organizational Behavior
Director, Ph.D. Program in Management

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
http://www.hec.unil.ch/people/jantonakis

Associate Editor:
The Leadership Quarterly
Organizational Research Methods
__________________________________________

On 29.10.2013 20:01, Adrian Stork wrote:
> Dear Stata friends,
>
> Sorry for asking but I've got the following problem(s):
> Starting with the actual issue I simply want to compare intercept
> values from 50 regressions with each other. I found the following
> post,
> http://www.stata.com/statalist/archive/2006-06/msg00837.html
> giving me almost the solution. It works perfectly fine for the
> coefficients but I don't know how to apply this test on the intercept.
> I tried
>
> suest regprice regmpg
> test [regprice_mean]intercept=[regmpg_mean]intercept but that doesn't work.
>
> In addition when I looked at the suest command in the description, I
> saw that it refers to "Seemingly unrelated estimation" what is
> actually what I wanted in the first place (running "sureg" over all 50
> dependent variables and compare intercepts) I received the error
> message "insufficient observations". Of couse, I know that I have
> quite a few missing values (i.e. the first dependent variable is
> complete with monthly 250 observations while the second one has merely
> 50 monthly observations, etc.). Still, when I running the SUR system
> with the first and second dependent variable (on independent variables
> with complete 250 observations), I get the error message "insufficient
> obs". When I'm running it with suest: everthing fine and I get a test
> statistic for the Null.
> So, in a nutshell, how can I test the intercepts with suest and is
> there a way to make "sureg" run although  I've got quite some missing
> values in the dependent variables?
>
> Best regards,
> Ad
> *
> *   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index