geolm function

Linear model for geostatistical data.

geolm creates a geostatistical linear model object of the appropriate class based on the arguments, especially the cmod arguments.

geolm(
  formula,
  data,
  coordnames,
  mod,
  weights = NULL,
  mu = NULL,
  longlat = NULL,
  cmod = NULL
)

Arguments

• formula: An object of class formula providing a symbolic description of the model to be fitted. See Details of this function and lm.
• data: A data frame containing the response, covariates, and location coordinates.
• coordnames: The columns of data containing the spatial coordinates, provided as a formula (e.g., ~ x + y), column numbers (e.g., c(1, 2)), or column names (e.g., c("x", "y"))
• mod: A model object produced by one of the cmod_* functions, e.g., cmod_std.
• weights: An optional vector of weights for the errors to be used in the fitting process. A vector that is proportional to the reciprocal variances of the errors, i.e., errors are assumed to be uncorrelated with variances evar/weights. Default is NULL, meaning that the weights are uniformly 1.
• mu: A single numeric value indicating the consant mean of the spatial process if simple kriging is desired. Default is NULL, meaning that ordinary or universal kriging should be used.
• longlat: A logical indicating whether Euclidean (FALSE) or Great Circle distance (WGS84 ellipsoid) (longlat = TRUE) should be used. Default is FALSE.
• cmod: Retained for backwards compatibility. A model object produced by one of the cmod_* functions, e.g., cmod_std.

Returns

Returns a geolm_* object, where *

depends on mod.

Details

Note: for the multiresolution Gaussian process model, if cmod$est == "f" (i.e., if the nugget is finescale instead of measurement error), then the weights

argument is internally set to rep(1, n), where n is the number of observations.

formula should be specified after the form y ~ x1 + x2, where y is the response variable and x1 and x2 are the covariates of interest. If mu is provided, the variables to the right of ~ are ignored.

Examples

data = data.frame(y = rnorm(10), x1 = runif(10),
                 x2 = runif(10))
d = geodist(data[,c("x1", "x2")])
mod = cmod_man(v = exp(-d), evar = 1)
gearmod = geolm(y ~ x1, data = data,
                coordnames = ~ x1 + x2, mod = mod)

Author(s)

Joshua French