rgeneric models

A framework for defining latent models in R

inla.rgeneric.define(model = NULL, debug = FALSE, ...)
inla.rgeneric.iid.model(
cmd = c("graph", "Q", "mu", "initial", "log.norm.const", "log.prior", "quit"),
theta = NULL)
inla.rgeneric.ar1.model(
cmd = c("graph", "Q", "mu", "initial", "log.norm.const", "log.prior", "quit"),
theta = NULL)
inla.rgeneric.wrapper(
cmd = c("graph", "Q", "mu", "initial", "log.norm.const", "log.prior", "quit"),
model, theta = NULL)
inla.rgeneric.q(
rmodel, 
cmd = c("graph", "Q", "mu", "initial", "log.norm.const", "log.prior", "quit"),
theta = NULL)

Arguments

model

The definition of the model; see inla.rgeneric.ar1.model

rmodel

The rgeneric model-object, the output of inla.rgeneric.define

debug

Logical. Turn on/off debugging

cmd

An allowed request

theta

Values of theta

...

Named list of variables that defines the environment of model

debug

Logical. Enable debug output

Value

This allows a latent model to be defined in R. See inla.rgeneric.ar1.model and inla.rgeneric.iid.model and the documentation for worked out examples of how to define latent models in this way. This will be somewhat slow and is intended for special cases and protyping. The function inla.rgeneric.wrapper is for internal use only.

Author

Havard Rue hrue@r-inla.org