[R-sig-Geo] Risk mapping: Parametric vs Non-Parametric Conditional Simulation approaches?

Zia Ahmed zua3 at cornell.edu
Fri Dec 18 17:00:51 CET 2009

I like to compare  areas not exceeding of  particular threshold values 
between parametric and non-parametric approaches of 1000 realizations. 
For non-parametric approach, I did IK for 1000 realizations (conditional 
simulation) and  calculated the area not exceeding (0.5 probability) of 
the threshold value for each of 1000 realizations.  Now,  I want to 
compare these areas with areas calculated from parametric approach.  For 
this,   I  did  OK  conditional simulation  of 1000 realizations. My 
question is: Is it possible to  create probability maps not exceeding a 
threshold value of  each of 1000 realizations. I know, I need variance 
of each prediction location of each realization to get the probability. 
Please  consider my  limited knowledge about theory of geostatistics.   
Any suggestion will be appreciated.  


-------------- next part --------------
A non-text attachment was scrubbed...
Name: zua3.vcf
Type: text/x-vcard
Size: 281 bytes
Desc: not available
URL: <https://stat.ethz.ch/pipermail/r-sig-geo/attachments/20091218/42b3076b/attachment.vcf>

More information about the R-sig-Geo mailing list