Estimation and Testing for Covariance-Spectral Spatial-Temporal Models

TL;DR

This paper investigates covariance spectral models for spatial-temporal data, focusing on estimation and testing methods, with an application to Irish wind speed data, enhancing understanding of spectral coherence across space and time.

Contribution

It provides deeper insights into Stein's semi-parametric model and introduces more intuitive estimation and testing techniques for covariance spectral spatial-temporal models.

Findings

Enhanced understanding of spectral coherence in spatial-temporal data

Development of simpler estimation and testing methods

Application to Irish wind speed data demonstrating practical utility

Abstract

In this paper we explore a covariance spectral modelling strategy for spatial-temporal processes which involves a spectral approach for time but a covariance approach for space.It facilitates the analysis of coherence between the temporal frequency components at different spatial sites. Stein(2005) developed a semi-parametric model within this framework.The purpose of this paper is to give a deeper insight into the properties of his model and to develop simple and more intuitive methods of estimation and testing. An example is given using the Irish wind speed data.