inlabru: materncov.bands – R documentation

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

materncov.bands

Matern correlation or covariance function approximate credible bands.

Description

Evaluate the covariance function for an inla.spde objectPlots the posterior distribution of the range, log(range), variance, or log(variance) parameter of a model's SPDE component. Can also plot Matern correlation or covariance function.

Usage

materncov.bands(
  manifold,
  dist,
  log.range,
  log.variance = NULL,
  alpha = 2,
  quantile = 0.95,
  n = 64,
  S1.L = NULL
)

Arguments

`manifold`	Either "R1", "S1", "R2", or "S2", from `mesh$manifold`, or a full `inla.mesh` or `inla.mesh.1d` object.
`dist`	A vector of distances at which to calculate the covariances/correlations
`log.range`	A scalar or a list (mean, sd), such as produced by `inla.spde.result(...)$summary.log.range.nominal[[1]][c("mean","sd")]`
`log.variance`	Either `NULL`, a scalar, or vector of the same type as for log.range. When `NULL`, the correlations are calculated instead of the covariances.
`alpha`	The SPDE operator order. Default 2.
`quantile`	The target credible probability. Default 0.95.
`n`	The number of parameter combinations to use for the approximation. Default 64.
`S1.L`	For `manifold` `"S1"`, give the length of the cyclic interval

Details

Uses a Gaussian assumption for the internal model parameters, and finds a region in parameter space with approximately quantile probability.

Value

A list with estimated covariance or correlation (when log.variance is NULL) functions:

`lower`	An approximate lower bound for the `quantile` credible region
`median`	The function for for the approximate median parameters quantile
`upper`	An approximate upper bound for the `quantile` credible region

Author(s)

Finn Lindgren Finn.Lindgren@ed.ac.uk

inlabru

Bayesian Latent Gaussian Modelling using INLA and Extensions

v2.3.1

GPL (>= 2)

Authors

Finn Lindgren [aut, cre, cph] (<https://orcid.org/0000-0002-5833-2011>, Finn Lindgren continued development of the main code), Fabian E. Bachl [aut, cph] (Fabian Bachl wrote the main code), David L. Borchers [ctb, dtc, cph] (David Borchers wrote code for Gorilla data import and sampling, multiplot tool), Daniel Simpson [ctb, cph] (Daniel Simpson wrote the basic LGCP sampling method), Lindesay Scott-Howard [ctb, dtc, cph] (Lindesay Scott-Howard provided MRSea data import code), Seaton Andy [ctb] (Andy Seaton provided testing and bugfixes)

Initial release