serp - Smooth Effects on Response Penalty for CLM
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) <doi:10.21105/joss.03705> and Ugba et al. (2021) <doi:10.3390/stats4030037>.
Last updated 3 months ago
categorical-dataordinal-regressionpenalized-regressionproportional-odds-regressionregularization-techniques
3.82 score 1 stars 44 scripts 1.5k downloadsgofcat - Goodness-of-Fit Measures for Categorical Response Models
A post-estimation method for categorical response models (CRM). Inputs from objects of class serp(), clm(), polr(), multinom(), mlogit(), vglm() and glm() are currently supported. Available tests include the Hosmer-Lemeshow tests for the binary, multinomial and ordinal logistic regression; the Lipsitz and the Pulkstenis-Robinson tests for the ordinal models. The proportional odds, adjacent-category, and constrained continuation-ratio models are particularly supported at ordinal level. Tests for the proportional odds assumptions in ordinal models are also possible with the Brant and the Likelihood-Ratio tests. Moreover, several summary measures of predictive strength (Pseudo R-squared), and some useful error metrics, including, the brier score, misclassification rate and logloss are also available for the binary, multinomial and ordinal models. Ugba, E. R. and Gertheiss, J. (2018) <http://www.statmod.org/workshops_archive_proceedings_2018.html>.
Last updated 2 years ago
brant-testbrier-scoreshosmer-lemeshow-testlikelihood-ratio-testlipsitz-testlog-loss-score-metriclogistic-regressionmisclassificationordinal-regressionproportional-odds-testpseudo-r2pulkstenis-robinson-test
3.18 score 2 stars 15 scripts 290 downloads