[R-sig-Geo] RandomFields: Randomness in realisations of sequential simulation?

[Edzer Pebesma]

Andre Jung wrote:
> Dear all,
>
> I've some general question regarding the implementation of
> randomness in RandomFields and sequential simulation.
My answers only apply to krige in package gstat; I believe this is what
you refer to with "sequential simulation".
>
> (1) Is there a difference between running
>    krige(nsim = 5, ....)
>     and running
>    krige(nsim = 1, ....)
>     for 5 times?
in the second case, 5 different random paths are followed.
>
> (2) Does repeating of the simulation with the same random number seed
>     (how to keep the seed?) lead to the same realisations? And: how
>     random is the path?
?set.seed
>
> (3) Can I fix the parameters (which ones?) to reproduce the same
>     realisations a later time?
?set.seed
>
>
> Another question is: How can I generate an 'e-type' of, let's say 10,
> realisations, and do some post-simulation analysis like defining
> probability to be above or below a certain threshold?
?apply ; I believe the asdar book has examples (see www.asdar-book.org)

>
>
> Many thanks in advance!
>
> best,
> Andre
>
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo

-- 
Edzer Pebesma
Institute for Geoinformatics (ifgi), University of Münster
Weseler Straße 253, 48151 Münster, Germany. Phone: +49 251
8333081, Fax: +49 251 8339763 http://ifgi.uni-muenster.de/
http://www.springer.com/978-0-387-78170-9 e.pebesma at wwu.de