A multivariate variance matrix for use with emulators

Hankin, R.K.S.. 2007 A multivariate variance matrix for use with emulators. Southampton, UK, National Oceanography Centre Southampton, 7pp.

Before downloading, please read NORA policies.

PDF
variancematrix.pdf
Restricted to NERC registered users only
Download (129kB)

Abstract/Summary

Conventional emulation considers a random field as a function of position in parameter space. This document shows how that framework may be generalized naturally to accommodate multivariate output. In the univariate case, a correlation matrix A is defined and the corresponding variance matrix is 2A, where 2 is a scalar. In the multivariate generalization presented here, the variance matrix contains a spatial component and an overall covariance component. The two-variable case is given first, followed by some simple examples. The method generalizes naturally to arbitrary numbers of variables.