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 at the end of May, and its replacement, statalist.org is already up and running.


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

st: standard errors under compound marginal effects


From   "Tim Burnett (ECO)" <Tim.Burnett@uea.ac.uk>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   st: standard errors under compound marginal effects
Date   Mon, 12 Nov 2012 18:28:49 +0000

Dear all,

I have a probit model where I am seeking to understand the compound marginal effect of a change in TWO independent (non-interacting) rhs variables. 

The command:

margins, dydx(a) at(b=3 c=4 d=5) - obviously gives the marginal effect and standard error of a change in 'a'

while:

margins, dydx(e) at(b=3 c=4 d=5) - gives the marginal effect and standard error of a change in 'e'

And because the variables enter into the probit independently then the total marginal effect is simply the sum of the above BUT is there a way to easily calculate the compound standard error? Although independently the change in each variable may be significant, I need to know if they cancel each other out...

I hope this makes sense.

Thanks,

Tim
--

Tim Burnett
PhD Researcher
Department of Economics & ESRC Centre for Competition Policy
University of East Anglia

Email: tim.burnett@uea.ac.uk
Phone: +44 (0) 7793 116 522
Skype: timb318
________________________________________
From: owner-statalist@hsphsun2.harvard.edu [owner-statalist@hsphsun2.harvard.edu] on behalf of sanja_lutzeyer@ncsu.edu [slutzey@ncsu.edu]
Sent: 12 November 2012 16:46
To: statalist@hsphsun2.harvard.edu
Subject: Re: st: Extracting numbers from code

Hi Nick.
Thank you for your reply.
That is indeed very useful code - thank you. I have tried it with one
of my questions which have less than 9 items and it works great!
The only real problem of identification is really with the number 1 -
which occurs in 1, 10 and 11.
I never have a question with more than 11 items.
Can you think of any way of any way around this?
Thanks a ton for your help.
Sanja
*
*   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