[eDebate] Edebate Comment about Joe's Rankings

Paul Strait paulstrait
Thu Apr 3 18:37:52 CDT 2008


The high/low thing seems to get at the problem only partially -- if someone is incorrectly ranking teams, all their scores should be rejected, not just the scores that are outliers with respect to a specific team (i.e., *all* their scores should be regarded as outliers, because they are interdependent).  It wouldn't be difficult to conduct multiple regression analysis to identify and eliminate bizarre rankings.  If one ranker's scores differ by a certain pre-set amount from the mean across the board (quantifying Hester's 'WTF'), their scores could be discounted.  There are several ways to do this, but it shouldn't be too difficult.
 
L. Paul Strait********************************Ph.D. Student,Annenberg School for CommunicationUniversity of Southern California********************************Cell: 202-270-6397
Email: strait at usc.edu 
_________________________________________________________________
Get in touch in an instant. Get Windows Live Messenger now.
http://www.windowslive.com/messenger/overview.html?ocid=TXT_TAGLM_WL_Refresh_getintouch_042008
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.ndtceda.com/pipermail/edebate/attachments/20080403/760a7180/attachment.htm 



More information about the Mailman mailing list