Gaussian predictive process models for large spatial data sets

By Sudipto Banerjee, Alan E. Gelfand, Andrew O. Finley, Huiyan Sang. Journal of The Royal Statistical Society Series B-statistical Methodology, 2008

1,128 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Environmental Engineering, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/17109f66d837ec59675fcef04cc072decc315f11

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Environmental Engineering

In Statistics and Probability

Citations in the corpus

Moving window kriging with geographically weighted variograms (2010, background): “Computationally, MWK–GWV is slightly more demanding than MWK–CV; and both models are affected by large datasets (a problem routinely encountered with numerous spatial methods, see Banerjee et al. 2008, for recent advances).”
Tapered Covariance: Bayesian Estimation and Asymptotics (2012, methodology): “Still another approach is to project the data onto a lower-dimensional space (Banerjee et al. 2008; Cressie and Johannesson 2008; Finley et al. 2009), although theoretical properties of these techniques are not known. Here, like Kaufman (2006), Kaufman, Schervish, and Nychka (2008), Zhang and Du (20”
Simultaneous Linear Quantile Regression: A Semiparametric Bayesian Approach (2012, methodology): “A sparse surrogate that has been successfully implemented in the context of density estimation (Tokdar 2007) and spatial statistics (Banerjee et al. 2008), replaces ω with a knot-based approximation ω∗(i, τ) = E [ω(i, τ) | W ∗ := {ω(j, τ∗ k ) : j = 1, 2, k = 0, 1, · · · , K}], where K is a prespecif”
Using temporal variability to improve spatial mapping with application to satellite data (2010, methodology): “, 1996; Nychka, Wikle & Royle, 2002; Kammann & Wand, 2003; Banerjee et al., 2008). Cressie & Johannesson (2006, 2008) proposed another solution, by defining a Spatial Random Effects (SRE) model that allows for a highly flexible class of spatial covariance functions and exact computation of the inver”
Multivariate convex regression with adaptive partitioning (2011, methodology): “irement, which does not scale well to larger datasets; the GP did not converge when n= 10;000 on Problem 2. Although one could use a low rank approximation, such as predictive processes (Tokdar 2007, Banerjee et al. 2008), such approaches are still computationally intensive and we do not consider th”
Bayesian Hierarchical Models With Conjugate Full-Conditional Distributions for Dependent Data From the Natural Exponential Family (2017, methodology): “…precise predictions in a computationally efficient manner (see, e.g., Wikle and Cressie, 1999; Cressie and Johannesson, 2006; Shi and Cressie, 2007; Banerjee et al., 2008; Cressie and Johannesson, 2008; Finley et al., 2009; Katzfuss and Cressie, 2011; Cressie et al., 2010a,b; Kang and Cressie,…”
Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations (2009, neutral): “…dependences can be achieved either by using a spatiotemporal covariate .s, t/ or a corresponding spatiotemporal Gaussian field (Kamman and Wand, 2003; Cressie and Johannesson, 2008; Banerjee et al., 2008; Finkenstadt et al., 2006; Abellan et al., 2007; Gneiting, 2002; Banerjee et al., 2004).”
Inhibitory geostatistical designs for spatial prediction taking account of uncertain covariance structure (2016, background): “Recent work on construction of designs that focus on the goals of efficient spatial prediction in conjunction with parameter estimation includes Banerjee et al. (2008), Bijleveld et al. (2012), Diggle and Lophaven (2006), Pilz and Spöck (2006), Zhu (2002), Zhu and Stein (2006) and Chipeta et al.”
Likelihood approximation with hierarchical matrices for large spatial datasets (2017, background): “, 2004, 2013) and spectral (Fuentes, 2007) domains, latent processes such as Gaussian predictive processes (Banerjee et al., 2008) and fixed-rank kriging (Cressie and Johannesson, 2008), and Gaussian Markov random-field approximations (Rue and Tjelmeland, 2002; Rue and Held, 2005; Fuglstad et al.”
Hierarchical statistical modeling of big spatial datasets using the exponential family of distributions (2013, methodology): “When the data are Gaussian, reducedrank-modeling approaches for the hidden Gaussian process Y (·) have been developed to deal with this computational challenge (e.g., Wikle et al., 2001; Cressie and Johannesson, 2006, 2008; Banerjee et al., 2008; Stein, 2008; Lopes et al., 2008).”
Towards novel approaches to modelling biotic interactions in multispecies assemblages at large spatial extents (2012, methodology): “For regression models a number of methods have been developed to describe spatial non-stationarity in parameter estimates by the modelling of one or more smooth surfaces over space (e.g. Fotheringham et al., 2002; Banerjee et al., 2008; Finley, 2011; Hothorn et al., 2011).”
Hierarchical Nearest-Neighbor Gaussian Process Models for Large Geostatistical Datasets (2014, methodology): “We cast a multivariate NNGP within a versatile spatially varying regression framework (Gelfand et al. 2003; Banerjee et al. 2008) and conveniently obtain entire posteriors for all model parameters as well as for the spatial processes at both observed and unobserved locations.”
Dimension reduction and alleviation of confounding for spatial generalized linear mixed models (2010, background): “den have resulted in an extensive literature detailing many approaches, e.g., process convolution (Higdon, 2002), xed rank kriging (Cressie and Johannesson, 2008), Gaussian predictive process models (Banerjee et al., 2008), covariance tapering (Furrer et al., 2006), and approximation by a Gaussian M”
Joint composite estimating functions in spatiotemporal models (2012, neutral): “A similar idea was exploited in Banerjee et al. (2008).”
Maximum likelihood estimation of spatially varying coefficient models for large data with an application to real estate price prediction (2020, methodology): “Currently available implementations of Bayesian approaches such as Gaussian predictive processes presented in Banerjee et al. (2008) or Gaussian Markov random field approximations by Lindgren et al.”