RE: st: tobit marginal effects

[Richard Williams <Richard.A.Williams.5@ND.edu>]

At 08:59 AM 7/21/2005 -0500, you wrote:
> Hi Richard,
>  Thank you for your fast response.  Unfortunately, I have tried
> downloading spostado, and prchange does not work for tobit.  I have
> asked the author of the routine, and he confirmed that it does not work,
>  Thanks again for your help,
>  Sandra
That is too bad!  Yes, a program has to be officially "blessed" before 
-spost- will work with it.  (I have that same problem with my -gologit2- 
program, which is why I include an option to make stored results compatible 
with -gologit-, which is supported by -spost-).  -tobit- probably could be 
supported, but obviously it is not a priority, at least at this point.

Two other things you might try:

1.  Use Stata's own -adjust- command.

2.  I think the way many -spost- routines work is they generate fake cases 
with the desired values, and then use the -predict- command to come up with 
the predicted values for those cases.

I demonstrate these approaches on pp. 6-9 of

http://www.nd.edu/~rwilliam/stats2/Logistic-Stata.pdf

When it works, -prchange- is nice because it will compute various values 
for you (e.g. the highest value of x, the lowest value), but you can 
compute those things yourselves and then plug them in where appropriate.


-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX:    (574)288-4373
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
WWW (personal):    http://www.nd.edu/~rwilliam
WWW (department):    http://www.nd.edu/~soc

*
*   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/