Package: boostmtree Version: 2.0.7 Date: 2026-10-20 Title: Boosted Multivariate Trees for Longitudinal Data Authors@R: c(person("Hemant", "Ishwaran", email = "hemant.ishwaran@gmail.com", role = "aut"), person("Amol", "Pande", email = "amoljpande@gmail.com", role = c("aut")), person("Udaya B.", "Kogalur", email = "ubk@kogalur.com", role = c("aut", "cre")), person("John", "Ehrlinger", email = "john.ehrlinger@gmail.com", role = "ctb")) Author: Hemant Ishwaran [aut], Amol Pande [aut], Udaya B. Kogalur [aut, cre], John Ehrlinger [ctb] Maintainer: Udaya B. Kogalur Depends: R (>= 4.3.0) Imports: randomForestSRC (>= 3.5.0), splines, nlme, parallel, RhpcBLASctl Suggests: testthat (>= 3.0.0) Config/testthat/edition: 3 Description: Implements Friedman's gradient descent boosting algorithm for modeling longitudinal response using multivariate tree base learners. Longitudinal response could be continuous, binary, nominal or ordinal. A time-covariate interaction effect is modeled using penalized B-splines (P-splines) with estimated adaptive smoothing parameter. Although the package is designed for longitudinal data, it can handle cross-sectional data as well. Implementation details are provided in Pande et al. (2017), Mach Learn . This is a Cleveland Clinic Foundation patched build correcting terminal-node coefficient divergence when fitting with cross-validation enabled. License: GPL (>=3) URL: https://ishwaran.org/, https://github.com/ehrlinger/boostmtree_src BugReports: https://github.com/ehrlinger/boostmtree_src/issues Config/pak/sysreqs: cmake libglpk-dev make libicu-dev libuv1-dev libxml2-dev libx11-dev Repository: https://ehrlinger.r-universe.dev Date/Publication: 2026-10-20 14:28:15 UTC RemoteUrl: https://github.com/ehrlinger/boostmtree_src RemoteRef: v2.0.7-ccf RemoteSha: b90180e4aab5fd67ab048bb20edc8c5c19956602 RemoteSubdir: boostmtree NeedsCompilation: no Packaged: 2026-10-20 19:49:13 UTC; root