From: Pierre G. <goo...@te...> - 2009-02-17 14:12:22
|
Dear Sara, The practical range of the exponential model in S-GeMS corresponds to what is called the "effective" range in Gslib. The choice of indicator kriging versus multiGaussian kriging depends on several factors, and the shape of the histogram might not be the critical one. Factors include the existence of a large proportion of observations with the same value (e.g. data below the detection limit), or the asymmetry in the spatial continuity of low and high values. In all situations, cross-validation could help deciding which method to adopt.. These last few months I have been involved with the modeling of contaminated sediments at several sites and multiGaussian kriging was adopted based on cross-validation results. Also, I recently published a paper in Computers & Geosciences and the associated computer code that implements all the steps of indicator kriging, including the modeling of all indicator variograms & cross-validation/jack-knife with generation of accuracy plots, automatically. Regards, Pierre On Tue, Feb 17, 2009 at 6:00 AM, sara sabri <sar...@ya...> wrote: > Dear list > waht is the range of an exponential model in s-gems? i.e. practical range > should be used? Is it the same with GSLIB? > And finally with a data of relatively normal distribution which methods > should I use to model the conditional probability? Is SISIM justified? Or I > have to use it only in case of asymetric distribution of categorical > variable? > I really appreiate your comments. > Thanks in advance > Sara > > ------------------------------ > New Email addresses available on Yahoo! > <http://sg.rd.yahoo.com/aa/mail/domainchoice/mail/signature/*http://mail.promotions.yahoo.com/newdomains/aa/> > Get the Email name you've always wanted on the new @ymail and @rocketmail. > Hurry before someone else does! > > > ------------------------------------------------------------------------------ > Open Source Business Conference (OSBC), March 24-25, 2009, San Francisco, > CA > -OSBC tackles the biggest issue in open source: Open Sourcing the > Enterprise > -Strategies to boost innovation and cut costs with open source > participation > -Receive a $600 discount off the registration fee with the source code: > SFAD > http://p.sf.net/sfu/XcvMzF8H > _______________________________________________ > Sgems-users mailing list > Sge...@li... > https://lists.sourceforge.net/lists/listinfo/sgems-users > > -- Pierre Goovaerts Chief Scientist at BioMedware Inc. 516 North State Street Ann Arbor, MI 48104 Voice: (734) 913-1098 (ext. 8) Fax: (734) 913-2201 Courtesy Associate Professor, University of Florida Geostatistician, Computer Sciences Corporation President, PGeostat LLC 710 Ridgemont Lane Ann Arbor, MI 48103 Voice: (734) 668-9900 Fax: (734) 668-7788 http://goovaerts.pierre.googlepages.com/ |