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: Factor variables


From   Maarten Buis <maartenlbuis@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Factor variables
Date   Mon, 18 Feb 2013 09:27:06 +0100

You might want to look at: M.L. Buis (2012) "Stata tip 106: With or
without reference", The Stata Journal, 12(1), pp. 162-164.
<http://www.maartenbuis.nl/publications/ref_cat.html>

-- Maarten

On Sun, Feb 17, 2013 at 11:08 PM, M.H.Hussein <mhh5@kentforlife.net> wrote:
> Thanks Richard.
>
> In the command line, I have three variables and the interaction terms between each and a dummy (gt287). Using this command line I am getting the estimates for the coefficients for the variables when i.gt287=0 and the coefficients for the interaction terms.
>
> To calculate the coefficients for the variables when i.gt287=1, I am adding the coefficients for each variable (when igt287=0) and the coefficient for the respective interaction terms (i.e. difference)
>
> My question is how I can get the standard errors for the calculated coefficients-i.e when i.gt287=1?
>
> Hope this is clearer.
>
> Thanks again,
> Mohamud
> ________________________________________
> From: owner-statalist@hsphsun2.harvard.edu [owner-statalist@hsphsun2.harvard.edu] on behalf of Richard Goldstein [richgold@ix.netcom.com]
> Sent: 17 February 2013 21:47
> To: statalist@hsphsun2.harvard.edu
> Subject: Re: st: Factor variables
>
> I do not find this entirely clear; however, if you look at the help file
> (-h fvvarlist-), under the "base levels" section, you will see that
> "ibn." means "no base level" and this might be what you want
>
> do realize, however, that you are changing the null hypotheses for your
> tests
>
> Rich
>
> On 2/17/13 4:39 PM, M.H.Hussein wrote:
>> Hello Statalisters
>>
>> I am running the regression command line below which contains factor variables with interactions. The command line returns coefficients for all variables in the model when the indicator gt287=0 and interaction terms.
>>
>>  xtreg  TCOST  i.gt287##c.P_O i.gt287##c.Y_TCOST10 i.gt287##c.enforcement10, fe
>>
>>
>> I would to obtain the estimates for coefficients when gt287=1 alongside above estimates, so that I can get standard errors and t statistics for all coefficients.
>>
>> Could you tell me if this possible and if so how I can write the command to get all estimates in a single command line?
>>
>> Thanks,
>> Mohamud
>> -- Kentforlife.net - the email service for alumni of the University of Kent
> *
> *   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/
>
> -- Kentforlife.net - the email service for alumni of the University of Kent
>
>
> *
> *   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/



-- 
---------------------------------
Maarten L. Buis
WZB
Reichpietschufer 50
10785 Berlin
Germany

http://www.maartenbuis.nl
---------------------------------

*
*   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