Ralph and Mary Otis Isham
Department of Statistics and the College
My research focuses on statistical models and methods for spatial
and spatial-temporal processes. In
particular, I am interested in the nature of the spatial-temporal
interactions implied by these models
and on developing statistical methods for assessing these interactions.
My main motivation for studying spatial-temporal processes is
to describe variations in the physical
environment. Some of the processes my collaborators and I are currently
studying include stratospheric
ozone, surface meteorology at high temporal resolution and climate at
a range of spatial and temporal scales.
A major component of my research in recent years is on analysis of massive
spatial-temporal datasets and on the resulting computational challenges
I am particularly interested in approaches to approximating likelihoods
for Gaussian process models in which the resulting covariance matrices
are large, dense and unstructured.
I am working with numerical analysts to bring to bear the best methods
in numerical linear algebra to the approximation of Gaussian likelihoods.