Another RNG question

Article View: sci.math.stat

Article #512

#512

From: mglacy
Date: Fri, 16 Oct 1992 19:59

16 lines
1275 bytes

I've been trying out a new RNG code. It appears to yield  a very
nice random u.r.v (0,1).  (At least it looks fine under k-s tests,
which is sufficient for my purposes.)  However,  when I use it  to
generate uniformly distributed random *integers*, it produces lousy
results.  I've just been multiplying each random real by 
some N, and then truncating the result to an integer. To make
the range be 1..N, I've then been adding 1 to the truncated result.

Any suggestions on why might be going wrong here?  Is this to
be expected?

Thanks.
=-=-=-=-=-=-=-=-=-==-=-=-=
Mike Lacy, Sociology Dept.      CSU and I have a deal: We don't take
Colo. State Univ.               responsibility for one another's opinions.
Fort Collins CO 80523           voice (303) 491-6721

Technical Details

Message-ID: <Oct16.195957.45264@yuma.ACNS.ColoState.EDU>

Path:

arc1-ca.pugleaf.net!sparky!uunet!know!hri.com!ukma!darwin.sura.net!zaphod.mps.ohio-state.edu!sol.ctr.columbia.edu!destroyer!ncar!csn!yuma!lamar!mglacy

Show Full Headers

Complete Article Headers

Path: arc1-ca.pugleaf.net!sparky!uunet!know!hri.com!ukma!darwin.sura.net!zaphod.mps.ohio-state.edu!sol.ctr.columbia.edu!destroyer!ncar!csn!yuma!lamar!mglacy
From: mglacy@lamar.ColoState.EDU
Newsgroups: sci.math.stat
Subject: Another RNG question
Message-ID: <Oct16.195957.45264@yuma.ACNS.ColoState.EDU>
Date: 16 Oct 92 19:59:57 GMT
Sender: news@yuma.ACNS.ColoState.EDU (News Account)
Organization: Colorado State University, Fort Collins, CO  80523
Lines: 16
Nntp-Posting-Host: lamar.acns.colostate.edu