checkRF {CoSMoS} | R Documentation |
Compares generated random fields sample statistics with the theoretically
expected values (similar to checkTS
). It also returns graphical output for
visual check.
checkRF(RF, lags = 30, nfields = 49, method = "stat")
RF |
output of |
lags |
number of lags of empirical STCF to be considered in the graphical output (default set to 30) |
nfields |
number of fields to be used in the numerical and graphical output (default set to 49). As the plots are arranged in a matrix with nrows as close as possible to ncol, we suggest using values such as 3x3, 3x4, 7x8, etc. |
method |
report method - |
## The example below refers to the fitting and simulation of 10 random fields
## of size 10x10 with AR(1) temporal correlation. As the fitting algorithm has
## O((mxm)^3) complexity for a mxm field, this setting allows for quick fitting
## and simulation (short CPU time). However, for a more effective visualization
## and reliable performance assessment, we suggest to generate a larger number
## of fields (e.g. 100 or more) of size about 30X30. This setting needs more
## CPU time but enables more effective comparison of theoretical and
## empirical statistics. Sizes larger than about 50x50 can be unpractical
## on standard machines.
fit <- fitVAR(
spacepoints = 10,
p = 1,
margdist ='burrXII',
margarg = list(scale = 3, shape1 = .9, shape2 = .2),
p0 = 0.8,
stcsid = "clayton",
stcsarg = list(scfid = "weibull", tcfid = "weibull",
copulaarg = 2,
scfarg = list(scale = 20, shape = 0.7),
tcfarg = list(scale = 1.1, shape = 0.8))
)
sim <- generateRF(n = 12,
STmodel = fit)
checkRF(RF = sim,
lags = 10,
nfields = 12)