Package: spStack 1.1.3.99

spStack: Bayesian Geostatistics Using Predictive Stacking

Fits Bayesian hierarchical spatial and spatial-temporal process models for point-referenced Gaussian, Poisson, binomial, and binary data using stacking of predictive densities. It involves sampling from analytically available posterior distributions conditional upon candidate values of the spatial process parameters and, subsequently assimilate inference from these individual posterior distributions using Bayesian predictive stacking. Our algorithm is highly parallelizable and hence, much faster than traditional Markov chain Monte Carlo algorithms while delivering competitive predictive performance. See Zhang, Tang, and Banerjee (2025) <doi:10.1080/01621459.2025.2566449>, and, Pan, Zhang, Bradley, and Banerjee (2025) <doi:10.1214/25-BA1582> for details.

Authors:Soumyakanti Pan [aut, cre], Sudipto Banerjee [aut]

spStack_1.1.3.99.tar.gz
spStack_1.1.3.99.zip(r-4.7)spStack_1.1.3.99.zip(r-4.6)spStack_1.1.3.99.zip(r-4.5)
spStack_1.1.3.99.tgz(r-4.6-x86_64)spStack_1.1.3.99.tgz(r-4.6-arm64)spStack_1.1.3.99.tgz(r-4.5-x86_64)spStack_1.1.3.99.tgz(r-4.5-arm64)
spStack_1.1.3.99.tar.gz(r-4.7-arm64)spStack_1.1.3.99.tar.gz(r-4.7-x86_64)spStack_1.1.3.99.tar.gz(r-4.6-arm64)spStack_1.1.3.99.tar.gz(r-4.6-x86_64)
spStack_1.1.3.99.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
spStack/json (API)

# Install 'spStack' in R:
install.packages('spStack', repos = c('https://span-18.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/span-18/spstack-dev/issues

Pkgdown/docs site:https://span-18.github.io

Uses libs:
  • openblas– Optimized BLAS
  • c++– GNU Standard C++ Library v3
Datasets:
  • sim_stvcPoisson - Synthetic point-referenced spatial-temporal Poisson count data simulated using spatially-temporally varying coefficients
  • simBinary - Synthetic point-referenced binary data
  • simBinom - Synthetic point-referenced binomial count data
  • simGaussian - Synthetic point-referenced Gaussian data
  • simPoisson - Synthetic point-referenced Poisson count data

On CRAN:

Conda:

openblascpp

5.62 score 1 stars 24 scripts 614 downloads 18 exports 53 dependencies

Last updated from:9f8d20e484. Checks:13 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-devel-arm64OK249
linux-devel-x86_64OK221
source / vignettesOK344
linux-release-arm64OK256
linux-release-x86_64OK216
macos-release-arm64OK169
macos-release-x86_64OK343
macos-oldrel-arm64OK202
macos-oldrel-x86_64OK328
windows-develOK182
windows-releaseOK210
windows-oldrelOK200
wasm-releaseOK185

Exports:candidateModelscholUpdateDelcholUpdateDelBlockcholUpdateRankOneget_stacking_weightsiDistposteriorPredictrecoverGLMscalesim_spDataspGLMexactspGLMstackspLMexactspLMstackstackedSamplerstvcGLMexactstvcGLMstacksurfaceplotsurfaceplot2

Dependencies:abindbackportsBHcheckmateclarabelclicodetoolscpp11CVXRdigestdistributionalfarverfuturefuture.applygenericsggplot2globalsgluegmpgtablehighsisobandlabelinglatticelifecyclelistenvloomagrittrMatrixmatrixStatsMBAnumDerivosqpparallellypillarpkgconfigposteriorR6RColorBrewerRcppRcppEigenrlangrstudioapiS7scalesscsslamtensorAtibbleutf8vctrsviridisLitewithr

Posterior Predictive Inference
Prediction in spatial linear model | Prediction in spatial generalized linear model | Prediction in spatially-temporally varying coefficients model
Rendered fromposterior-predictive.Rmdusingknitr::rmarkdown

Last update: 2026-05-18
Started: 2025-07-08

Spatial Regression Models
Bayesian Gaussian spatial regression models | Using fixed hyperparameters | Leave-one-out predictive densities using PSIS | Using predictive stacking | Analyzing samples from the stacked posterior | Analysis of spatial non-Gaussian data | Spatial Poisson count data | Under fixed hyperparameters | Posterior recovery of scale parameters | Sampling from stacked posterior | Spatial binomial count data | Spatial binary data | References
Rendered fromspatial.Rmdusingknitr::rmarkdown

Last update: 2026-05-18
Started: 2025-07-08

spStack: Bayesian Geostatistics Using Predictive Stacking
Bayesian Gaussian spatial regression models | Bayesian non-Gaussian spatial regression models | Additional functionalities | References
Rendered fromspStack.Rmdusingknitr::rmarkdown

Last update: 2026-05-18
Started: 2024-09-29

Spatial-Temporal Regression Models
Bayesian non-Gaussian spatially-temporally varying coefficient models | Formula for varying coefficients model | Using fixed hyperparameters | Independent processes | Independent shared processes | Multivariate processes | Using predictive stacking
Rendered fromspatial-temporal.Rmdusingknitr::rmarkdown

Last update: 2026-03-08
Started: 2025-07-08

Technical Overview
Introduction | Bayesian Gaussian spatial regression models | Bayesian non-Gaussian spatial regression models | Bayesian non-Gaussian spatial-temporal regression model | Predictive stacking | References
Rendered fromtechnical_overview.Rmdusingknitr::rmarkdown

Last update: 2025-07-11
Started: 2025-07-08

Readme and manuals

Help Manual

Help pageTopics
spStack: Bayesian Geostatistics Using Predictive StackingspStack-package spStack
Create a collection of candidate models for stackingcandidateModels
Different Cholesky factor updatescholUpdate cholUpdateDel cholUpdateDelBlock cholUpdateRankOne
Optimal stacking weightsget_stacking_weights
Calculate distance matrixiDist
Prediction of latent process at new spatial or temporal locationsposteriorPredict
Recover posterior samples of scale parameters of spatial/spatial-temporal generalized linear modelsrecoverGLMscale
Simulate spatial data on unit squaresim_spData
Synthetic point-referenced spatial-temporal Poisson count data simulated using spatially-temporally varying coefficientssim_stvcPoisson
Synthetic point-referenced binary datasimBinary
Synthetic point-referenced binomial count datasimBinom
Synthetic point-referenced Gaussian datasimGaussian
Synthetic point-referenced Poisson count datasimPoisson
Univariate Bayesian spatial generalized linear modelspGLMexact
Bayesian spatial generalized linear model using predictive stackingspGLMstack
Univariate Bayesian spatial linear modelspLMexact
Bayesian spatial linear model using predictive stackingspLMstack
Sample from the stacked posterior distributionstackedSampler
Bayesian spatially-temporally varying generalized linear modelstvcGLMexact
Bayesian spatially-temporally varying coefficients generalized linear model using predictive stackingstvcGLMstack
Make a surface plotsurfaceplot
Make two side-by-side surface plotssurfaceplot2