Re: st: RE: Normal CDF

[Carlos Aller <caller@merlin.fae.ua.es>]

El 14/11/2011 12:05, Nick Cox escribió:
> I think you want -normal(x - A)-.
>
> Nick
> n.j.cox@durham.ac.uk
>
> Carlos Aller
>
> Do you know how to compute the Normal CDF for the non-standard case? I
> mean, Stata provides "normal(x)", assuming standard normal (0,1), but
> I'd like to compute normal x, for a normal distribution (A,1), where A
> is different from zero.
>
>
> *
> *   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/
I need that the argument of the function is as negative as possible in 
order to ensure concavity of the likelihood function I am estimating. 
For this, I need a probit with a very negative cut-off, and I get this 
with a normal (-1000,1), for example.
Carlos.
*
*   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/