A new specification of generalized linear models for categorical data

2014/04/29 by Jean Peyhardi, Peyhardi, Jean, Catherine Trottier +3 · 2 citations
Computer Science · Decision Sciences · Mathematics · #Bayesian Modeling and Causal Inference #Data Management and Algorithms #FOS: Computer and information sciences #Methodology (stat.ME) #Multi-Criteria Decision Making #stat.ME

paper · pdf · doi:10.48550/arxiv.1404.7331

31 pages, 13 figures

openalex publication_date 2014/04/29 · arxiv created 2014/05/12 · arxiv updated 2014/05/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01

Abstract

Regression models for categorical data are specified in heterogeneous ways. We propose to unify the specification of such models. This allows us to define the family of reference models for nominal data. We introduce the notion of reversible models for ordinal data that distinguishes adjacent and cumulative models from sequential ones. The combination of the proposed specification with the definition of reference and reversible models and various invariance properties leads to a new view of regression models for categorical data.

Citations

• Sequential item response models with an ordered response

Cited by

• What is an Ordinal Latent Trait Model?
• Discrete Responses in Bivariate Generalized Additive Models

Related

• Partitioned conditional generalized linear models for categorical data
• Multinomiale, ordinale und stereotype logistische Regression – eine Einführung in die Regressionsanalyse kategorialer Zielvariablen
• Generalized Orthogonal Components Regression for High Dimensional Generalized Linear Models
• Context-specific independencies for ordinal variables in chain regression models
• Optimal Scaling transformations to model non-linear relations in GLMs with ordered and unordered predictors