Talk:Rand index

What is the n representing? Also, wouldn't it be easier as:
 * $$R=\frac{|X\cap Y|}{|X|}=\frac{|X\cap Y|}{|Y|}$$

, assuming their cardinalities are equal, |X| = |Y|? Or am I misinterpreting this article? because |X intersect Y| is the number of elements that are in both X and Y, and |X| is the total number of elements. EulerGamma 00:08, 7 September 2006 (UTC)
 * The article was a bit confusing because it didn't mention that it's pairs of elements you're looking at. It should make more sense now. -SpuriousQ 11:07, 9 December 2006 (UTC)

Adjusted-for-chance
Can somebody explain in the article what that means, maybe by taking the explanation which can be found in the article about Adjusted Mutual Information? I'm no expert and I have no time for now, sorry. --Blaisorblade (talk) 03:39, 7 March 2009 (UTC)

Merger proposal
I see this merger is here for over a year. I just performed it, I hope people will have a look at it and correct any errors. Talgalili (talk) 09:59, 11 December 2010 (UTC)
 * The merge was fine.--Kudpung (talk) 02:31, 12 December 2010 (UTC)
 * Thank you Kudpung - and thanks for doing the other language corrections. Talgalili (talk) 05:54, 12 December 2010 (UTC)

References?
I don't see the point of including K. Y. Yeung & W. L. Ruzzo, "Principal component analysis for clustering gene expression data" in the Reference section. I mean, of course, it is a nice paper, but it wouldn't it be better to refere to papers that accually are about clustering and quality measures for clustering? The Yeung paper is an application paper for a very narrow audience, i.e. people in bioinformatics. A much better reference for people who want to learn something about clustering would be for example Meila, M. "Comparing clusterings by the variation of information", 2003 or something like that. There are tons of papers like this out there. 60.226.180.105 (talk) 23:28, 5 January 2011 (UTC)
 * Good point - please do go a head and do the changes :) Talgalili (talk) 08:56, 6 January 2011 (UTC)
 * Notionally the point would be obvious if it appeared as an in-line citation, so that we could see why someone might be interested in looking at it. But the article is about the Rand index and adjusted Rand index, not immediately about clustering, so that any application of these indices is potentially good not just clustering. The article should point anyone "who wants to learn something about clustering" to one of the clustering articles, although showing how the indices are used in clustering would be good here. Melcombe (talk) 09:41, 6 January 2011 (UTC)