Package: rsDCM
Type: Package
Title: Robust and Sparse Dynamic Causal Modelling for Functional MRI
Version: 0.2.0
Date: 2026-11-08
Authors@R: c(
    person(given = "Godfred", family = "Arhin",
           email = "arhin0122@gmail.com",
           role = c("aut", "cre", "trl")),
    person(given = "Nilotpal", family = "Sanyal",
           email = "nsanyal@utep.edu",
           role = "aut"),
    person(given = "SPM25 Authors", role = c("ctb", "cph"),
           comment = "Original MATLAB SPM25 (v25.01.02) implementation; see LICENSE.note"))
Maintainer: Godfred Arhin <arhin0122@gmail.com>
Description: Fits robust and sparse group-level Dynamic Causal Models (DCMs)
    for functional magnetic resonance imaging data. The group method combines
    a Student-t likelihood with a Gaussian-spike and nonlocal product-moment
    slab prior, propagates first-level posterior covariance through block
    pre-whitening, fits empirical-Bayes modes by multistart generalized
    expectation-maximization with conditional maximization, and integrates
    posterior inclusion probabilities by parallel-tempering Monte Carlo
    (<doi:10.48550/arXiv.2609.06379>). The package also provides an R port of
    deterministic single-state DCM and Parametric Empirical Bayes routines
    from 'SPM25' (version 25.01.02), based on Friston et al. (2003)
    <doi:10.1016/S1053-8119(03)00202-7>.
License: GPL-2
Encoding: UTF-8
LazyData: true
LazyDataCompression: xz
Depends: R (>= 4.0.0)
Imports: Matrix, Rcpp, expm, MASS, methods, stats, utils
LinkingTo: Rcpp
Suggests: testthat (>= 3.0.0), knitr, rmarkdown, R.matlab, withr
URL: https://kay202.github.io/rsDCM/
BugReports: https://github.com/Kay202/rsDCM/issues
VignetteBuilder: knitr
Config/testthat/edition: 3
Config/roxygen2/version: 7.3.3
NeedsCompilation: yes
RoxygenNote: 7.3.3
Packaged: 2026-11-13 20:45:10 UTC; nsanyal
Author: Godfred Arhin [aut, cre, trl],
  Nilotpal Sanyal [aut],
  SPM25 Authors [ctb, cph] (Original MATLAB SPM25 (v25.01.02)
    implementation; see LICENSE.note)
Repository: CRAN
Date/Publication: 2026-11-14 15:50:14 UTC
