calc_prec_matrix: Compute n by n covariance matrix W over n grid cells

In mapn/DAbayes: Bayesian Statistical Model for Climate-Change Detection and Attribution

Description

This function computes the covariance matrix of the ensemble members for the measured variable, which is a fixed diagonal matrix with diagonal elements equal to the empirical variance of the corresponding ensemble memebers. Further work will allow W to be a more general matrix (e.g., based on a GMRF) with unknown parameters

Usage

calc_prec_matrix(neighborhood_matrix, gamma)

Arguments

neighborhood_matrix	an n by n neighborhood matrix for n grid cells
gamma	a real valued parameter in covariance matrix W

Value

an n by n covariance matrix

Author(s)

Pulong Ma <[e-mail]>

Examples

n <- 30  # number of grid cells over the globe
neighborhood_matrix <- Matrix::sparseMatrix(1:n, 1:n, x=rep(1,n))
gamma <- 0.1
W <- calc_prec_matrix(neighborhood_matrix, gamma)
Matrix::image(W, xlab="", ylab="", cex=0.5, cex.lab=0.6)

mapn/DAbayes documentation built on May 21, 2019, 11:26 a.m.