On Thursday 19 July 2007, sara sabri wrote: > Dear all > In generating simulation, e.g. sequential Gaussian simulation the first > step is to define a random path through all grid nodes as each point > visited only once. My question is why it is said define if it is a random > path???
Hi Sara, and list, I'm not positive about your question, so I'll answer a few things: 1. A conventional definition of a path would be an ordered series of spatially adjacent locations. This is not what is meant here. In this case, the path is an ordered sequence of nodes at which simulations will be made. The order need not be sequentially spatially adjacent; indeed, the results might not be very satisfying if that were done, since each node simulation is conditioned on nearby, previously simulated nodes. 2. Interestingly, I think many implementations don't employ a (pseudo) random path, but rather use a nested grid sort of pattern. The main point is that you don't want to, say, begin in the upper left corner, process each node in the row, and then move on to the next row.... There's a brief discussion of some of these issues in Goovaerts (1997) p. 379, as well I'm sure in other textbooks (someone has run off with my edition of Chiles & Delfiner, and I'm less familiar with others). Goovaerts, P. (1997) Geostatistics for Natural Resources Evaluation. -- Ashton Shortridge Associate Professor [EMAIL PROTECTED] Dept of Geography http://www.msu.edu/~ashton 235 Geography Building ph (517) 432-3561 Michigan State University fx (517) 432-1671 + + To post a message to the list, send it to [email protected] + 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/
