Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

# Re: st: erfc function

 From Nick Cox To statalist@hsphsun2.harvard.edu Subject Re: st: erfc function Date Wed, 2 May 2012 15:14:21 +0100

```I am not sure of the distinction you are making here, but my guess is that

1. Uses of erf() and erfc() are concentrated highly in various parts
of physical science and associated parts of applied mathematics and
typically refer to applications outside data analysis and statistical
modelling. These are prime areas for e.g. Mathematics, MATLAB but less
so for e.g. Stata.

2. Whenever Stata users want erf() or erfc() they usually figure out
quickly that they are transformations of Stata's -normal()- function.

Nick

On Wed, May 2, 2012 at 2:45 PM, Heyman, James E. <JEHEYMAN@stthomas.edu> wrote:
> Thanks much.  In retrospect, I would have saved a lot of time going for a bespoke solution rather than searching for a built-in one.
>
>
>
> James E. Heyman, PhD
> Associate Professor of Marketing
> University of St. Thomas
> 1000 LaSalle Ave (TMH443N)
> Minneapolis, MN  55403
>
>   ___o
>  `\  <,_
> @ /  @
>
>
> On May 2, 2012, at 1:49 AM, Maarten Buis wrote:
>
> --- On Wed, May 2, 2012 at 12:51 AM, Heyman, James E. wrote:
> I feel like an idiot for asking but can somebody please tell me where the erfc (complementary error function) is in Stata?
>
> --- On Wed, May 2, 2012 at 2:07 AM, Nick Cox wrote:
> Look at e.g.
>
> . twoway function 2 * (1  - normal(x)) , ra(-10 10)
>
> Alternatively:
>
> twoway function 2 * normal(-x) , ra(-10 10)
>
> With this version you are a bit less likely to be bitten by precision
> problems, see:
>
> William Gould (2006) Mata Matters: Precision, The Stata Journal, 6(4): 550-560.
> <http://www.stata-journal.com/article.html?article=pr0025>
>

*
*   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/
```