Description Usage Arguments Details Value Author(s) References
Unreviewed
1 2 3 4 5 6 |
coords |
coordinates of the sites where functional data are observed (dim: s by 2) |
data |
matrix with values for the observed functions (dim: m by s) |
argnames |
a character vector of length three containing: the name of the argument (argvals), a description of the sites (coord), the name of the observed function values. |
one.model |
logical, indicates whether the cross validation is going to be done just one model or one model for each site. Deafult is TRUE. See details below. |
smooth.type |
a string with the name of smoothing method to be applied to |
array.nbasis |
array with values for the number of elements in the cubic B-spline basis. |
argvals |
a set of argument values. (length: m) |
array.lambda |
array of penalization parameters for smoothing the observed functions. |
cov.model |
a string with the name of the correlation function. Default is NULL, see |
fix.nugget |
logical, indicating whether the |
nugget |
value for the nugget parameter. |
fix.kappa |
logical, indicating whether the |
kappa |
value of the smoothness parameter. |
max.dist.variogram |
a numerical value defining the maximum distance considered when fitting the variogram. |
Validation models
The parameter one.model
is used to define the models used in the cross validation:
If it is TRUE
, a model and smoothed data are created before the beginning and used inside the cross validation process.
If it is FALSE
, then for each site a model and smoothed data are created and used on each iteration.
A list with the following components:
k.opt |
unreviewed |
l.opt |
unreviewed |
krig.cv |
unreviewed |
mse.cv |
unreviewed |
mse.cv.opt |
unreviewed |
fd.models |
unreviewed |
Ramon Giraldo rgiraldoh@unal.edu.co,
Pedro Delicado pedro.delicado@upc.edu,
Jorge Mateu mateu@mat.uji.es.
Giraldo, R. (2009) Geostatistical Analysis of Functional Data. Ph.D. thesis. Universitat Politecnica de Catalunya.
Giraldo, R., Delicado, P. and Mateu, J. (2012) geofd: An R package for function-valued geostatistical prediction. Revista Colombiana de Estadistica. 35, 385-407.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.