I think I've figured out why I was getting different results for the different random cases. One case was randomizing with a non-uniform distribution while another was using a uniform distribution.

8~)

 


--- On Fri, 1/22/10, Billy <billyx5@gmail.com> wrote:

From: Billy <billyx5@gmail.com>
Subject: Re: [Skunkworks] random sampling
To: "Skunkworks Forum" <skunkworks@lists.my.co.ke>
Date: Friday, January 22, 2010, 5:03 PM


The items in the sorted set arent randomized.  so even if you access
them randomly -- the output is always biased since the original number
distribution was biased.

I fail to see your logic here. What bias? Would the same bias still exist if I were to access a randomized set sequentially? 

-----Inline Attachment Follows-----

_______________________________________________
Skunkworks mailing list
Skunkworks@lists.my.co.ke
http://lists.my.co.ke/cgi-bin/mailman/listinfo/skunkworks
------------
Skunkworks Server donations spreadsheet
http://spreadsheets.google.com/ccc?key=0AopdHkqSqKL-dHlQVTMxU1VBdU1BSWJxdy1fbjAwOUE&hl=en
------------
Skunkworks Rules
http://my.co.ke/phpbb/viewtopic.php?f=24&t=94
------------
Other services @ http://my.co.ke
Other lists
-------------
Announce: http://lists.my.co.ke/cgi-bin/mailman/listinfo/skunkworks-announce
Science:  http://lists.my.co.ke/cgi-bin/mailman/listinfo/science
kazi:     http://lists.my.co.ke/cgi-bin/mailman/admin/kazi/general