Authors: A. K. Ramesh, Neelam Sakya
Abstract: Spatial and spatiotemporal statistics have become essential tools for analyzing data that exhibit dependence across space and time. Such data arise naturally in diverse fields including environmental science, epidemiology, urban planning, climate studies, agriculture, and public health. Unlike classical statistical methods that assume independence among observations, spatial and spatiotemporal models explicitly account for correlation structures induced by geographic proximity and temporal evolution. This paper presents a comprehensive review of the theoretical foundations, methodological developments, and practical applications of spatial and spatiotemporal statistics. Key topics discussed include spatial autocorrelation, variogram modeling, geostatistical methods, lattice-based models, point process analysis, and spatiotemporal extensions. Modern computational techniques and challenges related to large-scale data are also examined. The paper aims to provide a unified overview suitable for researchers and practitioners from engineering mathematics, statistics, and applied sciences.
Keywords: Spatial statistics; Spatiotemporal modeling; Geostatistics; Spatial autocorrelation; Gaussian random fields; Environmental data analysis
Full Issue
| View or download the full issue | PDF 16-26 |