See also the following essays in the J Wiki: http://www.jsoftware.com/jwiki/Essays/Normal_CDF http://www.jsoftware.com/jwiki/Essays/Extended_Precision_Functions (8 Error Function and 9 Normal CDF).
----- Original Message ----- From: Eugene McDonnell <[EMAIL PROTECTED]> Date: Monday, January 15, 2007 9:28 pm Subject: Re: [Jprogramming] Generating simplified normal distributions > > On Jan 15, 2007, at 8:46 PM, Eldon Eller wrote: > > > Given my probably wrong understanding of your question, it seems > to > > me that all you have to do is take a standard normal > distribution > > (mean=0, sd=1), multiply it by the empirical sd to give a normal > > > distribution with mean=0 and sd=empirical sd, then add the > > empirical mean to give a normal distribution with mean=empirical > > > mean and sd=empirical sd. > > Vector 10.3, January 2003 has my article "Beware Scholes". The > Black- > Scholes formula led to a Nobel Prize in economics in 1997 for > Myron > Scholes, his colleague Fischer Black having died. Excuse me if > this > is impertinent. > > Ewart Shaw uses the confluent hypergeometric conjunction in his > erf, > and uses erf in his cumulative distribution function of the normal > > distribution: > erf =: (*&(%:4p_1)%^@:*:)*[:1 H. 1.5*: NB. A&S 7.1.21 (right) > > cnd =: [:-:1:+[:erf%&(%:2) NB. A&S 26.2.29 (solved for P) ---------------------------------------------------------------------- For information about J forums see http://www.jsoftware.com/forums.htm
