Recall that in Stata pi = 3.14159... is accessible to machine precision
as either _pi or c(pi). So there is no harm done,
and possibly some small harm avoided, in using those
inbuilt constants directly.
Nick
n.j.cox@durham.ac.uk
Jhilbe@aol.com
> I found an approximation to the Bessel Type 2 in an old
> journal article.
> Since it is an approximation anyhow, I further simplified it
> by calculating pi/2
> and pi/4 to their numeric values (to 4 decimal points),
> which are 1.5708 and
> 0.7854 respectively. The actual approximation I found was given as:
> J_n(x) ~ sqrt(2/(pi*x)) * sin(x-(2*n+1)*(pi/4).
>
*
* 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/