Spatio-temporal change of support modeling with R
- PDF / 1,679,331 Bytes
- 32 Pages / 439.37 x 666.142 pts Page_size
- 53 Downloads / 170 Views
Spatio-temporal change of support modeling with R Andrew M. Raim1 · Scott H. Holan2,3 · Jonathan R. Bradley4 · Christopher K. Wikle2 Received: 2 January 2020 / Accepted: 26 August 2020 © This is a U.S. government work and not under copyright protection in the U.S.; foreign copyright 2020
Abstract Spatio-temporal change of support methods are designed for statistical analysis on spatial and temporal domains which can differ from those of the observed data. Previous work introduced a parsimonious class of Bayesian hierarchical spatio-temporal models, which we refer to as STCOS, for the case of Gaussian outcomes. Application of STCOS methodology from this literature requires a level of proficiency with spatiotemporal methods and statistical computing which may be a hurdle for potential users. The present work seeks to bridge this gap by guiding readers through STCOS computations. We focus on the R computing environment because of its popularity, free availability, and high quality contributed packages. The stcos package is introduced to facilitate computations for the STCOS model. A motivating application is the American Community Survey (ACS), an ongoing survey administered by the U.S. Census Bureau that measures key socioeconomic and demographic variables for various populations in the United States. The STCOS methodology offers a principled approach to compute model-based estimates and associated measures of uncertainty for ACS variables on customized geographies and/or time periods. We present a detailed case study with ACS data as a guide for change of support analysis in R, and as a foundation which can be customized to other applications. Keywords American Community Survey · Areal data · Basis functions · Bayesian statistics · Model-based estimates · Official statistics
1 Introduction In the course of an analysis where data are inherently spatio-temporal, an investigator may desire estimates on spatial and/or temporal domains not coinciding exactly with domains of the observations. This can include customized geographies and time Electronic supplementary material The online version of this article (https://doi.org/10.1007/s00180020-01029-4) contains supplementary material, which is available to authorized users.
B
Andrew M. Raim [email protected]
Extended author information available on the last page of the article
123
A. M. Raim et al.
periods conceived long after the data have been collected. Spatio-temporal change of support methods aim to provide this capability. A methodology recently proposed by Bradley et al. (2015b) captures spatio-temporal dependencies in areal data by constructing several key matrices which become the foundation of a Bayesian hierarchical model. Model fitting is done via Markov chain Monte Carlo (MCMC); in particular, the model permits a Gibbs sampler which is conveniently composed of draws from standard distributions. Estimates, predictions, and appropriate measures of uncertainty are provided by the fitted model. This methodology, hereafter referred to as the STCOS mod
Data Loading...
