Restricted Covariance Priors with Applications in Spatial Statistics
نویسندگان
چکیده
منابع مشابه
Restricted Covariance Priors with Applications in Spatial Statistics.
We present a Bayesian model for area-level count data that uses Gaussian random effects with a novel type of G-Wishart prior on the inverse variance- covariance matrix. Specifically, we introduce a new distribution called the truncated G-Wishart distribution that has support over precision matrices that lead to positive associations between the random effects of neighboring regions while preser...
متن کاملCovariance Tapering in Spatial Statistics
In the analysis of spatial data, the inverse of the covariance matrix needs to be calculated. For example, the inverse is needed for best linear unbiased prediction or kriging, and is repeatedly calculated in the maximum likelihood estimation or the Bayesian inferences. Since the spatial sample size can be quite large, operations on the large covariance matrix can be a numerical challenge if no...
متن کاملMethods for Estimating Heterogeneous Spatial Covariance Functions with Environmental Applications
Estimation of spatial covariance is important to many statistical problems in the analysis of environmental monitoring data. In this Chapter we review several difrerent methods for spati.al covariance estimation from monitoring data, with emphasis on methods for heterogeneous models. We briefly describe some applications, and outline how these methods can be extended to space-time and multivari...
متن کاملGaussian Markov Random Field Models With Applications in Spatial Statistics
Gaussian Markov Random Field (GMRF) models are frequently used in statistics, and in spatial statistics in particular. The analytical properties of the Gaussian distribution are convenient and the Markov property invaluable when constructing single site Markov chain Markov Carlo algorithms. Rue (2001) demonstrates how numerical methods for sparse matrices can be utilised to construct efficient ...
متن کاملAnalysis of Drought Spatial Statistics in Iran
Drought is one of the environmental events and an inseparable part of climatic fluctuations. This phenomenon is one of the main characteristics of the various climates. Awareness of spatiotemporal behavior is effective in land planning. The spatial statistical methods provide the means by which they analyze the spatial patterns of random variables such as precipitation. In this study, using the...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Bayesian Analysis
سال: 2015
ISSN: 1936-0975
DOI: 10.1214/14-ba927