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: Standar error of discrete change probit model


From   "Dimitriy V. Masterov" <[email protected]>
To   [email protected]
Subject   Re: st: Standar error of discrete change probit model
Date   Tue, 31 Jan 2012 15:40:39 -0500

Noam,

Take a look at margeff from ssc, as well as the Stata Journal paper
about it. The paper contains a section on dummy variables, and margeff
has a dummies option to calculate exactly what you want.

DVM

On Tue, Jan 31, 2012 at 3:30 PM, NOAM MANO <[email protected]> wrote:
> I want to write my own do file to compute the marginal effect of
> discrete change in probit model.
> Following
>
> David M. Drukker(2010) ; 2010 Italian Stata Users Group meeting
> Bologna November 2010
> (http://www.stata.com/meeting/italy10/drukker_sug.pdf)
>
> Using margins to estimate partial effects
> probit crash tickets traffic i.male, nolog
>
>
> Or using hand
>
>  generate double xb0 = _b[tickets]*tickets + _b[traffic]*traffic + _b[_cons]
>  generate double de = normal(xb0 + _b[1.male]) - normal(xb0)
>  summarize de
>
> The mean of de give the marginal effect. We use stata function margin
> ( margins , dydx(male), we will have the same value of the marginal
> effect. However the standard error is different from the one obtained
> by summarized de.
> My question is: how to compute the standar error by hand.
>
> I have tried this:
>
> (normalden(xb0 + _b[1.male]) +normalden(xb0) )^2 *var(_b[1.male])
>
> But I am not sure if it's good.
> Your help will be very appreciated
>
> *
> *   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index