Dear List, Here are the responses I have received to date concerning the matter above.
Thanks to all Stuart ================================================== Hi Stuart I believe that the PCA methodology is most commonly used for multivariate data, due to its simplicity. You might want to refer to: "Multivariate Geostatistics" by Hans Wackernagal, published by Springer. A linear transformation is defined which transforms a set of correlated variables into uncorrelated factors. These orthogonal factors can then be shown to extract successively a maximal part of the total variance of the variables. God luck, Mark Mark G Sweeney Rio Tinto Technical Services (TS) Principal Consultant 1 Research Avenue Bundoora, 3083 Australia Phone: (+61) 3 9242 3278 Mobile: 0407 357 877 mailto: [EMAIL PROTECTED] ================================================== Dear Stuart. I good reference paper is: Geostatistical Simulations of regio0nalized Pore-Size Distributions Using Min?Max Autocorrelation Factors. A. J. Desbarats and R. Dimitrakopoulos Mathematical Geology Vol. 32, N 8 2000 p 919-942 Cheers M�rcio Bastos Fonseca [EMAIL PROTECTED] =================================================== There was a tech report from Stanford Univ. Stat Dept about 1984 by Paul Switzer and Green, I think it subsequently appeared as a paper in the Canadian J. Statistics but 8-10 yrs later. I think Paul is still at Stanford so you could contact him there. They were looking at multispectral data, Landsat I think. Somthing that might be close as well 1995, Tailiang Xie and Myers, D.E., Fitting Matrix valued variogram models by simultaneous diagonalization: I Theory. Math. Geology 27, 867-876 1995,Tailiang Xie, Myers, D.E. and Long, A.E., Fitting Matrix valued variogram models by simultaneous diagonalization: II Applications. Math. Geology 27, 877-888 Donald E. Myers <http://www.u.arizona.edu/~donaldm> ======================================================= Is the following reference useful ? Gregoire PS: Sorry, I don't have the paper but could find the following abstact in a database. ++++++++++++++++++++++++++++++++++++++++++++++++++ Journal: Remote Sensing of Environment Volume 64, Issue 1 April 1998 Pages 1-19 Title: Multivariate Alteration Detection (MAD) and MAF Postprocessing in Multispectral, Bitemporal Image Data: New Approaches to Change Detection Studies Authors: Allan A. Nielsena, Knut Conradsena and James J. Simpsonb Abstract This article introduces the multivariate alteration detection (MAD) transformation which is based on the established canonical correlations analysis. It also proposes using postprocessing of the change detected by the MAD variates using maximum autocorrelation factor (MAF) analysis. The MAD and the combined MAF/MAD transformations are invariant to linear scaling. Therefore, they are insensitive, for example, to differences in gain settings in a measuring device, or to linear radiometric and atmospheric correction schemes. Other multivariate change detection schemes described are principal component type analyses of simple difference images. Case studies with AHVRR and Landsat MSS data using simple linear stretching and masking of the change images show the usefulness of the new MAD and MAF/MAD change detection schemes. Ground truth observations confirm the detected changes. A simple simulation of a no-change situation shows the accuracy of the MAD and MAF/MAD transformations compared to principal components based methods. Gregoire Dubois [[EMAIL PROTECTED]] ============================================================ Stuart Masters Principal Consultant - Geology & Geostatistics Rio Tinto Technical Services Level 25, Central Park 152 -158 St. Georges Terrace Perth, WA, Australia 6000 Ph: + 61 8 9327 2984 FAX: + 61 8 9327 2999 Mob: 0438 394 380 -- * To post a message to the list, send it to [EMAIL PROTECTED] * As a general service to the users, please remember to post a summary of any useful responses to your questions. * To unsubscribe, send an email to [EMAIL PROTECTED] with no subject and "unsubscribe ai-geostats" followed by "end" on the next line in the message body. DO NOT SEND Subscribe/Unsubscribe requests to the list * Support to the list is provided at http://www.ai-geostats.org
