> The problem with the old linear congruential generator is not 
> the period, which is long enough perhaps, ...

Tell that to the people who complained that the GB_FLIP
period (_1+2^55) is not long enough.



----- Original Message -----
From: Henry Rich <[email protected]>
Date: Tuesday, February 23, 2010 13:28
Subject: Re: [Jgeneral] GB_Flip RNG seed
To: General forum <[email protected]>

> The problem with the old linear congruential generator is not 
> the 
> period, which is long enough perhaps, but its behavior when used 
> to 
> create random vectors.  If I am creating random points in n-
> dimensional 
> space using (10000,n) (?...@$) 1000000 for example, it will be 
> found that 
> the points do not sample the space uniformly, but instead 
> cluster along 
> [hyper]planes in the space.  This can miss details in the 
> model being 
> analyzed.
> 
> Henry Rich
> 
> Roger Hui wrote:
> > Please read the vocabulary page for ?
> > http://www.jsoftware.com/help/dictionary/d640.htm
> > In particular the part for 9!:44 and 9!:45.
> > The RNGs now in use in J can not be completely 
> > determined by a "seed" which is a single integer.
> > 
> > If you are pining for the old linear conguenial generator,
> > here it is:
> > 
> >    tick =: [ <....@%~ (* 3 : 
> 'qrl=:(<:2^31)|(7^5)*qrl')@]>    roll =: 
> (<:2^31)&tick"0>    qrl  =: 16807
> > 
> > I understand that it, with its period of _1+2^31, is totally
> > unacceptable for modern usage.  Some users have
> > also complained that GB_Flip has too short a period
> > (_1+2^55).
> > 
> > 
> > 
> > ----- Original Message -----
> > From: Brian Schott <[email protected]>
> > Date: Tuesday, February 23, 2010 5:33
> > Subject: [Jgeneral] GB_Flip RNG seed
> > To: [email protected]
> > 
> >>    The following behavior is unexpected for the GB_Flip
> >> RNG. Notice that the verb `roll` produces the same seed
> >> every time instead of updating the seed each time as is
> >> required for most simulation studies, for example those that
> >> employ the random components in batches. Also, in order to
> >> perform a simulation study which synchronizes the random
> >> fractions in order to achieve "variance reduction", an
> >> important strategy, and for other research studies to
> >> replicate exactly the fractions.
> >>    The earlier versions of J updated the seed after
> >> each usage. Only with the implementation of the newer RNG's
> >> was this feature changed. I request that the old behavior be
> >> restored at least for GB_Flip.
> >>
> >>    9!:43]1
> >>    9!:0''
> >> 16807
> >>    roll=: monad define
> >> i=:0
> >> for. i. y do. ? y
> >> i=:>:i
> >> smoutput i,9!:0''
> >> end.
> >> )
> >>    roll 10
> >> 1 16807
> >> 2 16807
> >> 3 16807
> >> 4 16807
> >> 5 16807
> >> 6 16807
> >> 7 16807
> >> 8 16807
> >> 9 16807
> >> 10 16807
> >>    9!:42''
> >> 1
----------------------------------------------------------------------
For information about J forums see http://www.jsoftware.com/forums.htm

Reply via email to