s-news
[Top] [All Lists]

Re: runif function and extreme values:

To: aldi@wubios.wustl.edu
Subject: Re: runif function and extreme values:
From: rossini@blindglobe.net (A.J. Rossini)
Date: 24 Oct 2002 13:18:00 -0700
Cc: s-news <s-news@wubios.wustl.edu>
In-reply-to: <3DB85581.2040509@wubios.wustl.edu>
References: <3DB85581.2040509@wubios.wustl.edu>
Reply-to: rossini@u.washington.edu
User-agent: Gnus/5.0808 (Gnus v5.8.8) XEmacs/21.4 (Honest Recruiter)
>>>>> "aldi" == Aldi Kraja <aldi@wubios.wustl.edu> writes:


    aldi> I am testing a random die. By using runif the two extreme values 1 and
    aldi> 6 are showing with less values compared with the numbers 2,3,4, and
    aldi> 5. Is there any good reason for it to happen?

Of course.  1 and 6 corresponds to 1/2-unit distances, the other 4 to
1 unit distances (6-1 = 5, sum of distances = 0.5 + 0.5 + 1 + 1 + 1 +
1). 

I would expect 1 and 6 to occur half as often (individually) as the
other 4 might. 

best,
-tony

-- 
A.J. Rossini                            Rsrch. Asst. Prof. of Biostatistics
U. of Washington Biostatistics          rossini@u.washington.edu        
FHCRC/SCHARP/HIV Vaccine Trials Net     rossini@scharp.org
-------------- http://software.biostat.washington.edu/ ----------------
FHCRC: M: 206-667-7025 (fax=4812)|Voicemail is pretty sketchy/use Email
UW:   Th: 206-543-1044 (fax=3286)|Change last 4 digits of phone to FAX
(my tuesday/wednesday/friday locations are completely unpredictable.)




<Prev in Thread] Current Thread [Next in Thread>