Type: Package Package: serp Title: Smooth Effects on Response Penalty for CLM Version: 0.2.5 Authors@R: person(given = "Ejike R.", family = "Ugba", role = c("aut", "cre", "cph"), email = "ejike.ugba@outlook.com", comment = c(ORCID = "0000-0003-2572-0023")) Description: Implements a regularization method for cumulative link models using the Smooth-Effect-on-Response Penalty (SERP). This method allows flexible modeling of ordinal data by enabling a smooth transition from a general cumulative link model to a simplified version of the same model. As the tuning parameter increases from zero to infinity, the subject-specific effects for each variable converge to a single global effect. The approach addresses common issues in cumulative link models, such as parameter unidentifiability and numerical instability, by maximizing a penalized log-likelihood instead of the standard non-penalized version. Fitting is performed using a modified Newton's method. Additionally, the package includes various model performance metrics and descriptive tools. For details on the implemented penalty method, see Ugba (2021) and Ugba et al. (2021) . License: GPL-2 URL: https://github.com/ejikeugba/serp BugReports: https://github.com/ejikeugba/serp/issues Depends: R (>= 4.1.0) Imports: ordinal (>= 2016-12-12), crayon, stats Suggests: covr, testthat, tibble, vctrs, pkgdown, VGAM (>= 1.1-10) Encoding: UTF-8 LazyData: True RoxygenNote: 7.3.2 Repository: https://ejikeugba.r-universe.dev Date/Publication: 2024-11-25 13:36:42 UTC RemoteUrl: https://github.com/ejikeugba/serp RemoteRef: HEAD RemoteSha: b6eec7672acb0ec14c916093459b72554f361939 NeedsCompilation: no Packaged: 2026-10-05 09:14:03 UTC; root Author: Ejike R. Ugba [aut, cre, cph] (ORCID: ) Maintainer: Ejike R. Ugba