2017
DOI: 10.1016/j.spasta.2017.08.004
|View full text |Cite
|
Sign up to set email alerts
|

Spatial subsemble estimator for large geostatistical data

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
17
0

Year Published

2018
2018
2022
2022

Publication Types

Select...
4
2
1
1

Relationship

0
8

Authors

Journals

citations
Cited by 26 publications
(17 citation statements)
references
References 26 publications
0
17
0
Order By: Relevance
“…Further, the assumption of independence across subregions allows the likelihood for β, θ and φ d is to be computed in parallel thereby facilitating computation. By way of distinction, this approach is inherently different from the "divide and conquer" approach (Liang et al, 2013;Barbian and Assunção, 2017). In the divide and conquer approach, the full dataset is subsampled, the model is fit to each subset and the results across subsamples are pooled.…”
Section: Spatial Partitioningmentioning
confidence: 99%
See 1 more Smart Citation
“…Further, the assumption of independence across subregions allows the likelihood for β, θ and φ d is to be computed in parallel thereby facilitating computation. By way of distinction, this approach is inherently different from the "divide and conquer" approach (Liang et al, 2013;Barbian and Assunção, 2017). In the divide and conquer approach, the full dataset is subsampled, the model is fit to each subset and the results across subsamples are pooled.…”
Section: Spatial Partitioningmentioning
confidence: 99%
“…For example, Paciorek et al (2015) show how (1.1) can be calculated using parallel computing while Katzfuss and Hammerling (2017) and Katzfuss (2017) develop a basisfunction approach that lends itself to distributed computing. Alternatively, Barbian and Assunc ¸ão (2017) and Guhaniyogi and Banerjee (2018) propose dividing the data into a large number of subsets, draw inference on the subsets in parallel and then combining the inferences. Datta et al (2016a,b) build upon Vecchia (1988) by developing novel approaches to factoring (1.1) as a series of conditional distributions based only on nearest neighbors.…”
Section: Introductionmentioning
confidence: 99%
“…Furthermore, any of the alternative approaches for approximating Gaussian process covariance matrices using reduced-rank or sparse parameterizations (e.g., Higdon, 2002;Furrer et al, 2006;Cressie and Johannesson, 2008;Lindgren et al, 2011;Gramacy et al, 2015;Nychka et al, 2015;Katzfuss, 2017) are also compatible with our PP-RB method, as long as they are applied in a Bayesian context (also see Heaton et al, ods (e.g., Liang et al, 2013;Kleiner et al, 2014;MacLaurin and Adams, 2015;Barbian and Assuncao, 2017) with PP-RB to reduce computational requirements further.…”
Section: Discussionmentioning
confidence: 99%
“…Over the last few decades the spatial statistics community has attacked this big GP problem from many fronts and offered many different and efficient solutions to ease the computational burden. Methods include sparse nearest neighbor approximations (Vecchia, 1988;Stein et al, 2004;Datta et al, 2016a), low-rank approximations (Banerjee et al, 2008;Cressie and Johannesson, 2008), sparse-plus-low-rank method (Ma et al, 2019), multi-resolutional approach (Katzfuss, 2017), data partitioning (Barbian and Assunção, 2017;Guhaniyogi and Banerjee, 2018), covariance tapering (Furrer et al, 2006;Kaufman et al, 2008), stochastic partial differential equations (Lindgren et al, 2011), composite likelihoods (Bevilacqua and Gaetan, 2015;Eidsvik et al, 2014), gridbased methods (Nychka et al, 2015;Guinness and Fuentes, 2017;Stroud et al, 2017), among others. A comprehensive review of all these methods is beyond the scope of this paper but we refer the readers to the articles Sun et al (2012); Bradley et al (2016); Banerjee (2017); Heaton et al (2019); Banerjee (2020) for reviews and comparisons of the methods.…”
Section: Introductionmentioning
confidence: 99%