it is wierd because it does not show anything when I put di A[1,2]
though the following you gave still works perfectly. I just changed
the main equation prob for etc... with my own equation and then mpg
with varmain but I dont' understand why I dont get anything in the
marg but just one zero.
sysuse auto, clear
prob for price mpg rep78 /*
*/ headroom trunk weight
ins mpg
loc uniq= r(N_unique)
su mpg, mean
prgen mpg, from(`r(min)') /*
*/ to(`r(max)') /*
*/ gen(prob) n(`uniq')
levelsof mpg
loc i 1
gen marg=0
foreach level in `r(levels)'{
mfx, var(mpg) at(mpg=`level')
mat A = e(Xmfx_dydx)
di A[1,2]
replace marg=A[1,2] in `i'
loc ++i
}
tw (connected probp1 probx), /*
*/ xti("Mpg") ytit("Probability") /*
*/ name(prob, replace) nodraw
tw (connected marg probx), /*
*/ xti("Mpg") ytit("Marginal Effect") /*
*/ name(marginal, replace) nodraw
gr combine prob marginal
N
On Mon, Sep 21, 2009 at 4:48 PM, Martin Weiss <[email protected]> wrote:
>
> <>
>
> -set trace on- just before you start cycling through the loop and watch for
> anything unusual. You could also put
>
>
> *************
> di A[1,2]
> *************
>
> inside the loop to see what it actually returns.
>
> HTH
> Martin
>
>
> -----Ursprüngliche Nachricht-----
> Von: [email protected]
> [mailto:[email protected]] Im Auftrag von Nirina F
> Gesendet: Montag, 21. September 2009 22:44
> An: [email protected]
> Betreff: Re: st: AW: why is this graph all over the place?
>
> No you are right, it is in [1,2].
> I put it back to [1,2].
> But I don't understand why I don't get the value of the marginal
> effects. all I get is:
> tab marg
>
> marg | Freq. Percent Cum.
> ------------+-----------------------------------
> 0 | 4,119 100.00 100.00
> ------------+-----------------------------------
> Total | 4,119 100.00
>
>
>
>
>
> *
> * 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/
