Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: Numerical accuracy of standard normal distribution
From
Georges Casamatta <[email protected]>
To
"[email protected]" <[email protected]>
Subject
st: Numerical accuracy of standard normal distribution
Date
Wed, 11 Sep 2013 06:49:48 +0000
Dear all,
I am coding a program for estimating a probit model using the IRLS algorithm. For this, I use the cumulative distribution function of the standard normal distribution in mata. I am surprised that it is equal to 1 for a value as small as 7 (the same kind of comment of course also applies to the density function). Isn't there a way to improve the numerical accuracy of this function ?
Thanks for your help,
Georges
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/