One suggestion from the FAQ " When I run mfx, I am getting the warning
message "warning: predict() expression unsuitable for standard-error
calculation; option nose imposed." What does that mean?" at:
http://www.stata.com/support/faqs/stat/mfx_nose.html
is to use the at() option.
In the example below, this results in the standard errors being calculated.
Scott
. sysuse auto,clear
(1978 Automobile Data)
. qui ivprobit fore price (mpg = weight)
. mfx , pred(p) varlist(mpg price)
warning: predict() expression p unsuitable for standard-error calculation;
option nose imposed
Marginal effects after ivprobit
y = Probability of positive outcome (predict, p)
= .23797014
-----------------------------------------------------------------------
variable | dy/dx X
-------------------------+---------------------------------------------
mpg | .0742097 21.2973
price | .0000736 6165.26
-----------------------------------------------------------------------
. mfx , pred(p) at(mpg=21.29729 ) varlist(mpg price)
warning: no value assigned in at() for variables price weight;
means used for price weight
Marginal effects after ivprobit
y = Probability of positive outcome (predict, p)
= .2379696
--------------------------------------------------------------------------
variable | dy/dx Std. Err. z P>|z| [ 95% C.I. ] X
---------+----------------------------------------------------------------
mpg | .0742096 .01001 7.41 0.000 .054588 .093831 21.2973
price | .0000736 .00002 4.07 0.000 .000038 .000109 6165.26
--------------------------------------------------------------------------
> -----Original Message-----
> From: [email protected] [mailto:owner-
> [email protected]] On Behalf Of Zuluaga, Blanca
> Sent: Thursday, February 09, 2006 8:09 AM
> To: [email protected]
> Subject: st: mfx ivprobit - ivoprobit
>
> Dear subscribers
>
> I would very much appreciate if one of you could help me to solve 2
> problems I have:
>
> 1) when I ask Stata to compute marginal effects after ivprobit, it shows
> me the same values of the coefficients in the regression. According to the
> stata help, it is possible to calculate mfx after ivprobit, but when I
> asked for that it tells me "warning: predict() expression unsuitable for
> standard-error calculation; option nose imposed"; and shows the
> coefficients as marginal effects.
>
> 2) is there any way to estimate an ORDERED probit model by using
> instrumental variables?
>
>
>
> Thanks a lot in advance
>
> Blanca Zuluaga
*
* 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/
