Package: SDALGCP2 0.1.1

Olatunji Johnson

SDALGCP2: Discrete Log-Gaussian Cox Processes for Aggregated Counts

Fits a spatially discrete approximation to a log-Gaussian Cox process model for spatially aggregated disease count data, estimated by Monte Carlo Maximum Likelihood as in Christensen (2004) <doi:10.1198/106186004X2525> and Johnson, Diggle and Giorgi (2019) <doi:10.1002/sim.8339>. Performance-critical steps (aggregated correlation assembly, Metropolis-adjusted Langevin algorithm (MALA) sampling, the Monte Carlo likelihood, and the Kronecker-structured space-time likelihood) are implemented in C++ via 'RcppArmadillo'. Provides a one-line, 'glm'-like interface and statistical extensions including a nugget term, general 'Matern' smoothness, raster and misaligned covariates, restricted spatial regression, importance-sampling diagnostics and re-anchored Monte Carlo maximum likelihood (MCML).

Authors:Olatunji Johnson [aut, cre], Emanuele Giorgi [aut], Peter Diggle [aut]

SDALGCP2_0.1.1.tar.gz
SDALGCP2_0.1.1.zip(r-4.7)SDALGCP2_0.1.1.zip(r-4.6)SDALGCP2_0.1.1.zip(r-4.5)
SDALGCP2_0.1.1.tgz(r-4.6-x86_64)SDALGCP2_0.1.1.tgz(r-4.6-arm64)SDALGCP2_0.1.1.tgz(r-4.5-x86_64)SDALGCP2_0.1.1.tgz(r-4.5-arm64)
SDALGCP2_0.1.1.tar.gz(r-4.7-arm64)SDALGCP2_0.1.1.tar.gz(r-4.7-x86_64)SDALGCP2_0.1.1.tar.gz(r-4.6-arm64)SDALGCP2_0.1.1.tar.gz(r-4.6-x86_64)
SDALGCP2_0.1.1.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
SDALGCP2/json (API)

# Install 'SDALGCP2' in R:
install.packages('SDALGCP2', repos = c('https://olatunjijohnson.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/olatunjijohnson/sdalgcp2/issues

Pkgdown/docs site:https://olatunjijohnson.github.io

Uses libs:
  • openblas– Optimized BLAS
  • c++– GNU Standard C++ Library v3
  • openmp– GCC OpenMP (GOMP) support library
Datasets:
  • liver - Primary biliary cirrhosis incidence in North East England
  • sdalgcp_data - Simulated aggregated disease-count data

On CRAN:

Conda:

openblascppopenmp

5.30 score 22 scripts 18 exports 48 dependencies

Last updated from:70d0bd499f. Checks:13 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-devel-arm64OK183
linux-devel-x86_64OK198
source / vignettesOK239
linux-release-arm64OK179
linux-release-x86_64OK202
macos-release-arm64OK203
macos-release-x86_64OK323
macos-oldrel-arm64OK199
macos-oldrel-x86_64OK338
windows-develOK168
windows-releaseOK175
windows-oldrelOK168
wasm-releaseOK177

Exports:coef_plotcontrol_mcmcexceedancelaplace_samplingmap_exceedancemc_diagnosticsmcml_fitmodel_checkphi_profileprecompute_corrreportsda_pointssdalgcpsdalgcp_controlSDALGCP2SDALGCP2_misalignedSDALGCP2_rasterSDALGCP2_ST

Dependencies:abindclassclassIntclicpp11crayonDBIdeldire1071farverggplot2gluegtablehmsisobandKernSmoothlabelinglatticelifecycleMASSMatrixpkgconfigpolyclipprettyunitsprogressproxyR6RColorBrewerRcppRcppArmadillorlangs2S7scalessfspatstat.dataspatstat.geomspatstat.randomspatstat.sparsespatstat.univarspatstat.utilstensorterraunitsvctrsviridisLitewithrwk

Spatial disease mapping with SDALGCP2
The model | The data | Fit | Map the two relative risks | Uncertainty and exceedance | A continuous surface | Model checking | Real data | Next
Rendered fromSDALGCP2-intro.Rmdusingknitr::rmarkdown

Last update: 2026-06-26
Started: 2026-06-16

Spatially continuous (raster) predictors
The problem, precisely | The data | Fitting: naive vs intensity-scale | When does it matter? | Output | Options
Rendered fromraster-covariates.Rmdusingknitr::rmarkdown

Last update: 2026-06-26
Started: 2026-06-16

Spatio-temporal disease mapping
The model | The data | Fit | Predict and map — pick a year and a quantity | Covariates and confounding | Tips
Rendered fromspatio-temporal.Rmdusingknitr::rmarkdown

Last update: 2026-06-26
Started: 2026-06-16

Estimating the spatial scale: grid vs continuous
Where (\phi) lives: a double integral | Set up an example | Grid (profile) | Continuous (direct) — the default | They agree — and continuous gives a standard error | Which to use?
Rendered fromscale-grid-vs-continuous.Rmdusingknitr::rmarkdown

Last update: 2026-06-26
Started: 2026-06-16

Spatial confounding and restricted spatial regression
The issue | Restricted spatial regression (RSR) | What RSR does — and what it does not | Practical guidance | References
Rendered fromspatial-confounding.Rmdusingknitr::rmarkdown

Last update: 2026-06-26
Started: 2026-06-16

Covariates measured on a different support
The method | Point support: monitoring stations | Areal support: a different partition | Notes
Rendered frommisaligned-covariates.Rmdusingknitr::rmarkdown

Last update: 2026-06-26
Started: 2026-06-16

Readme and manuals

Help Manual

Help pageTopics
Coefficient plot of fixed effects (and sigma^2) with confidence intervalscoef_plot
Wald confidence intervals for an SDALGCP2 fitconfint.SDALGCP2
MCMC control settings for the MALA samplercontrol_mcmc
Exceedance probabilities P(risk > threshold)exceedance
Sample the latent field [S | Y] (Poisson, non-nested) via C++ MALAlaplace_sampling
Primary biliary cirrhosis incidence in North East Englandliver
Map exceedance probabilities P(risk > threshold)map_exceedance
Importance-sampling diagnostics for an MCML fitmc_diagnostics
Monte Carlo maximum likelihood estimation for the spatial SDA-LGCPmcml_fit
Posterior-predictive model checking for an SDALGCP2 fitmodel_check
Profile likelihood and confidence interval for the spatial scale phiphi_profile
Map an sdalgcp fitplot.sdalgcp
Plot an SDALGCP2 fit (the phi profile deviance)plot.SDALGCP2
Map a fitted SDALGCP2 predictionplot.SDALGCP2_pred
Map a spatio-temporal prediction for one timeplot.SDALGCP2_ST_pred
Precompute aggregated region-level correlation matricesprecompute_corr
Predict relative risk from an sdalgcp fitpredict.sdalgcp
Predict relative risk from a fitted SDALGCP2 modelpredict.SDALGCP2
Discrete (region x time) prediction for a spatio-temporal fitpredict.SDALGCP2_ST
Print an SDALGCP2 fitprint.SDALGCP2
Print a summary of an SDALGCP2 fitprint.summary.SDALGCP2
One-call panel of post-fit graphicsreport
Generate candidate sampling points inside each regionsda_points
Fit a spatially discrete LGCP model for aggregated countssdalgcp
Control settings for 'sdalgcp'sdalgcp_control
Simulated aggregated disease-count datasdalgcp_data
Fit a spatial SDA-LGCP modelSDALGCP2
Fit an SDA-LGCP with covariates measured on a different supportSDALGCP2_misaligned
Fit an SDA-LGCP with spatially continuous (raster) covariatesSDALGCP2_raster
Fit a spatio-temporal SDA-LGCP model (Kronecker-free)SDALGCP2_ST
Summary of an SDALGCP2 fitsummary.SDALGCP2