Dynamic Multiscale Spatiotemporal Models for Gaussian Areal Data

Abstract

We introduce a new class of dynamic multiscale models for spatiotemporal processes arising from Gaussian areal data. Specifically, we use nested geographical structures to decompose the original process into multiscale coefficients which evolve through time following state space equations. Our approach naturally accommodates data that are observed on irregular grids as well as heteroscedasticity. Moreover, we propose a multiscale spatiotemporal clustering algorithm that facilitates estimation of the nested geographical multiscale structure. In addition, we present a singular forward filter backward sampler for efficient Bayesian estimation. Our multiscale spatiotemporal methodology decomposes large data analysis problems into many smaller components and thus leads to scalable and highly efficient computational procedures. Finally, we illustrate the utility and flexibility of our dynamic multiscale framework through two spatiotemporal applications. The first example considers mortality ratios in the state of Missouri whereas the second example examines agricultural production in Espírito Santo State, Brazil.

Bayesian hierarchical multi-subject multiscale analysis of functional MRI data

“…9 and the posterior variance for the wavelet coefficients, but at a potentially high computational cost. Another possible extension would be the application of recently developed multiscale spatiotemporal models (Ferreira et al, 2011) to the analysis of fMRI data. In addition to allowing for highly structured dependency among the components of the process of interest, these multiscale Reconstructed regression coefficients based on posterior means of wavelet coefficients for a subset of the scales of resolution: level 0 to level 3 (Column 1); level 0 to level 4 (Column 2); level 0 to level 5 (Column 3).…”

Regionalization of Multiscale Spatial Processes by Using a Criterion for Spatial Aggregation Error

“…() and Ferreira et al . ()). For reviews of ecological inference and image segmentation see Wakefield (), Waller and Gotway () and Ferreira and Lee ().…”

Dynamic Quantile Linear Models: A Bayesian Approach

“…During the last 30 years, many contributions, methodological and computational, have been introduced. The advent of stochastic simulation techniques stimulated applications of the state space methodology to model complex stochastic structures, like dynamic spatiotemporal models [15], dynamic survival models [3], dynamic latent factor models [28], and multiscale modeling [11,12]. A number of papers have recently appeared on the application of DLM to hydrology [10], intraday electricity load [30], finance [55], insurance and many other areas.…”