Agree, but I am more interested in similarity of
voters' ballots than similarity of candidates.
On 12/14/05, Paul Kislanko <[EMAIL PROTECTED]> wrote:
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of rob brown
Sent: Wednesday, December 14, 2005 6:11 PM
To: Paul Kislanko
Cc: Election Methods Mailing List
Subject: Re: [EM] number of possible ranked ballots given N candidatesI think it is possible, though, to use the combination of pairwise matrix
and the counts-by-rank matrix together to retrieve the the original ballot
preferences.
You could get a more accurate estimate of the original ballots than the matrix alone, but you can't get the original ballots.
For instance, I believe you have lost all the data about similarity of candidates.
---- election-methods mailing list - see http://electorama.com/em for list info
