Page 1 of 1

Blindfolding in M3

Posted: Mon Oct 02, 2006 10:56 am
by Michael Stolle
Dear all,

First of all: Thanks a lot for releasing M3, makes working so much more convenient!

Question: Results for communality and redundancy differ for the PLS report on the one hand and the blindfolding report on the other hand. Why is that? My understanding was that, unlike bootstrapping, the blindfolding procedure comes to consistent results?

Thanks

Michael

Posted: Mon Oct 02, 2006 11:15 am
by cringle
Hi,

there is a difference between "communality"/"redundancy" and "crossvalidated communality"/"crossvalidated redundancy". Check the literature on that issue, e.g. Tenenhaus et al. 2005 (viewtopic.php?t=21).

Best
Christian