prior.glm.control: Defines prior options

In geoRglm: A Package for Generalised Linear Spatial Models

Description

This auxiliary function defines prior options for pois.krige.bayes and binom.krige.bayes.

Usage

prior.glm.control(beta.prior = c("flat", "normal", "fixed"),
              beta = NULL, beta.var.std = NULL,
              sigmasq.prior = c("uniform", "sc.inv.chisq", "reciprocal", "fixed"),
              sigmasq = NULL, df.sigmasq = NULL,
              phi.prior = c("uniform", "exponential","fixed",
                            "squared.reciprocal", "reciprocal"),
              phi = NULL, phi.discrete = NULL,
              tausq.rel = 0)

Arguments

beta.prior	prior distribution for the mean (vector) parameter beta. The options are "flat" (default), "normal" or "fixed".
beta	hyper-parameter for the prior distribution of the mean (vector) parameter beta. Only used if beta.prior = "normal" or beta.prior = "fixed". For the latter beta defines the value of the known mean.
beta.var.std	standardised (co)variance hyperparameter(s) for the prior for the mean (vector) parameter beta. The (co)variance matrix for beta is given by the multiplication of this matrix by sigma^2. Only used if 'beta.prior = "normal"'.
sigmasq.prior	prior distribution for the parameter sigma^2. The options are "uniform" (default), "sc.inv.chisq", "reciprocal" (gives improper posterior), or "fixed".
sigmasq	fixed value of the parameter sigma^2 when sigmasq.prior = "fixed". Parameter in the scaled inverse-chi^2 prior distribution for sigma^2.
df.sigmasq	parameter in the scaled inverse-chi^2 prior distribution for sigma^2.
phi.prior	prior distribution for the range parameter phi. Options are: "uniform" (\propto 1), "exponential" (exp(- nu * phi)), "fixed" (known value of phi), "squared.reciprocal" (1/phi^2), "reciprocal" (1/phi). Alternativelly, a user defined discrete distribution can be specified by providing a vector of probabilities. These probabilities corrresponds to a prior distribution with support phi.discrete. If the "fixed" the argument phi should be provided and it is regarded as fixed when performing predictions.
phi	fixed value of the parameter phi when phi.prior = "fixed". Mean of the prior distribution when phi.prior = "exponential".
phi.discrete	support points for the discretisation of the prior for the parameter phi.
tausq.rel	the value of the relative nugget parameter tau_R^2. Default is tausq.rel = 0.

Value

A list with processed arguments to be passed to the main function.

Author(s)

Ole F. Christensen [e-mail],
Paulo J. Ribeiro Jr. [e-mail].

See Also

pois.krige.bayes and binom.krige.bayes.

geoRglm documentation built on May 2, 2019, 4:03 p.m.