predictionOnAGrid: Prediction of the response on a grid/raster

In suyunkang/PrevalenceMapping: Prevalence Mapping

Description

The function predicts the response on target locations where data are not observed using posterior distributions.

Usage

predictionOnAGrid(response, finalmodel, A_mat, spde, mesh,
  family = "binomial", raster_stack, nsamp, int.strategy,
  write_posterior = TRUE)

Arguments

response	A data frame containing the response data including number of positive cases (n_positive), number of individuals examined (examined), and point locations (longitude and latitude).
finalmodel	An object returned from the function findModelWithSmallestDIC.
A_mat	An observation/prediction weight matrix returned from makeMeshSPDE.
spde	An inla.spde2 model object for a Matern model returned from makeMeshSPDE,
mesh	A triangle mesh created based on initial point locations and returned from makeMeshSPDE.
family	A string indicating the likelihood family, Default: ‘binomial’.
raster_stack	A collection of RasterLayer objects with the same spatial extent and resolution.
nsamp	Number of samples to draw from an approximated posterior of a fitted model. Make nsamp >= 100 in order to compute mean, sd, IQR, and 95% CI of posterior samples.
int.strategy	Character. The integration strategy to use; one of ‘auto’, ‘ccd’, ‘grid’, ‘eb’ (empirical bayes), ‘user’ or ‘user.std’.
write_posterior	A logical argument indicating if posterior realizations are to be written into raster files, Default: TRUE.

Details

DETAILS

Value

OUTPUT_DESCRIPTION

Examples

## Not run: 
if(interactive()){
 #EXAMPLE1
 }

## End(Not run)

suyunkang/PrevalenceMapping documentation built on May 10, 2019, 1:52 a.m.