Define the stationary SPDE cgeneric model for INLA.

Usage

cgeneric_sspde(
  mesh,
  alpha,
  control.priors,
  constr = FALSE,
  debug = FALSE,
  useINLAprecomp = TRUE,
  libpath = NULL
)

Arguments

mesh: triangulation mesh to discretize the model.
alpha: integer used to compute the smoothness parameter.
control.priors: named list with parameter priors. This shall contain prange and psigma each one as a length two vector with (U, a) to define the PC-prior parameters such that P(range<U)=a and P(sigma>U)=a, respectively. See Fuglstad et. al. (2019) <DOI: 10.1080/01621459.2017.1415907>. If a=0 or a=NA, then U is taken to be the fixed value of the parameter.
constr: logical, default is FALSE, to indicate if the integral of the field over the domain is to be constrained to zero.
debug: integer, default is zero, indicating the verbose level. Will be used as logical by INLA.
useINLAprecomp: logical, default is TRUE, indicating if it is to be used the shared object pre-compiled by INLA. This is not considered if 'libpath' is provided.
libpath: string, default is NULL, with the path to the shared object.

Value

objects to be used in the f() formula term in INLA.

Note

This is the stationary case of INLA::inla.spde2.pcmatern() with slight change on the marginal variance when the domain is the sphere, following Eq. (23) in Lindgren et. al. (2024).

References

Geir-Arne Fuglstad, Daniel Simpson, Finn Lindgren & Håvard Rue (2019). Constructing Priors that Penalize the Complexity of Gaussian Random Fields. Journal of the American Statistical Association, V. 114, Issue 525.

Finn Lindgren, Haakon Bakka, David Bolin, Elias Krainski and Håvard Rue (2024). A diffusion-based spatio-temporal extension of Gaussian Matérn fields. SORT vol. 48, no. 1, pp. 3-66 <doi: 10.57645/20.8080.02.13>