statistics.predictive {geoR}R Documentation

Summary statistics from predictive distributions

Description

Computes summaries based on simulations of predictive distribution returned by krige.bayes and krige.conv.

Usage

statistics.predictive(simuls, mean.var = TRUE, quantile, threshold,
                      sim.means, sim.vars)

Arguments

simuls object with simulations from the predictive distribution
mean.var Logical. Indicates whether or not to compute mean and variances of the simulations at each location.
quantile defines quantile estimator. See documentation for output.control .
threshold defines probability estimator. See documentation for output.control.
sim.means Logical. Indicates whether or not to compute the mean of of the conditional simulations.
sim.vars Logical. Indicates whether or not to compute the variances of the conditional simulations.

Value

A list with one ore more of the following components.

mean mean at each prediction location.
variance variance at each prediction location.
quantiles quantiles, at each prediction location.
probabilities probabilities, at each prediction location, of been below the provided threshold.
sim.means vector with means of each conditional simulation.
sim.vars vector with variances of each conditional simulation.

Author(s)

Paulo J. Ribeiro Jr. paulojus@leg.ufpr.br,
Peter J. Diggle p.diggle@lancaster.ac.uk.

References

Further information on the package geoR can be found at:
http://www.legufpr.br/geoR.

[Package geoR version 1.6-27 Index]