Dear List: A reviewer (apparently a geostatistics expert) commented on the nugget effect in a conditional simulation (using sgsim) as follows:
"To maintain the observed values in the simulation process is synonymous with neglecting the nugget effect. For skewed data, the nugget effect can be considerably larger in observation space than in transformed N(0,1) space, and the omission of the nugget effect in the simulation procedure should be justified." I couldn't find reference to such synonymy in the Duetsch and Journal GSLIB book nor in Pierre Goovaerts book. Of course, the second sentence in the comment is true, but I still don't understand how a conditional simulation neglects the nugget. I used a nugget, based on the empirical nscore transformed variogram, of about 20%. This is included in the sgsim parameter file. Can someone explain to me in what way the conditional simulation procedure using sgsim is 'neglecting the nugget effect', or direct me to a reference? Thanks in advance for your help, Paul Walline National Marine Fisheries Service Alaska Fisheries Science Center + + To post a message to the list, send it to ai-geostats@jrc.it + To unsubscribe, send email to majordomo@ jrc.it with no subject and "unsubscribe ai-geostats" in the message body. DO NOT SEND Subscribe/Unsubscribe requests to the list + As a general service to list users, please remember to post a summary of any useful responses to your questions. + Support to the forum can be found at http://www.ai-geostats.org/
