Re: st: Multinominal logit. Marginal effects with non-linear terms.

["T.de Hoop" <T.deHoop@maw.ru.nl>]

I have two questions:
1. You have an y as dependent and an y as independent variable. Is that
a typo, or are you adding lagged y?

Sorry, this is a typo. 
2. In this case correct marginal effects has been used in different
ways in the literature. First, it can refer to not ignoring the square
or interaction terms. Second, it can refer to computing the average
marginal effects, instead of the marginal effect at average values of
the explanatory variables. Which do you mean?

I'm looking for the marginal effects at the mean values of the explanatory variables. I assume this can only be done using the first method wherein I do not ignore the square or interaction terms. 




Maarten buis schreef:

> --- "T.de Hoop" <T.deHoop@maw.ru.nl> wrote:
>   
> > I'm running an mlogit regression of this form:
> >  
> > y=a+b.x+c.x2+d.y+e.z+f.(y.z)+u
> >  
> > and I would like to know if any of the marginal effect commands can
> > help me to get the correct marginal effects for the variables x and
> > y, including the square term and the interaction. Do I have to do it
> > by hand otherwise??
> >     
> I have two questions:
> 1. You have an y as dependent and an y as independent variable. Is that
> a typo, or are you adding lagged y?
>
> 2. In this case correct marginal effects has been used in different
> ways in the literature. First, it can refer to not ignoring the square
> or interaction terms. Second, it can refer to computing the average
> marginal effects, instead of the marginal effect at average values of
> the explanatory variables. Which do you mean?
>
> Maarten
>
>
> -----------------------------------------
> Maarten L. Buis
> Department of Social Research Methodology
> Vrije Universiteit Amsterdam
> Boelelaan 1081
> 1081 HV Amsterdam
> The Netherlands
>
> visiting address:
> Buitenveldertselaan 3 (Metropolitan), room Z434
>
> +31 20 5986715
>
> http://home.fsw.vu.nl/m.buis/
> -----------------------------------------
>
>
> 	
> 	
> 		
> ___________________________________________________________ 
> New Yahoo! Mail is the ultimate force in competitive emailing. Find out more at the Yahoo! Mail Championships. Plus: play games and win prizes. 
> http://uk.rd.yahoo.com/evt=44106/*http://mail.yahoo.net/uk 
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
>   
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/