Partitioned conditional generalized linear models for categorical data - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Partitioned conditional generalized linear models for categorical data

Abstract

In categorical data analysis, several regression models have been pro-posed for hierarchically-structured response variables, such as the nested logit model. But they have been formally defined for only two or three levels in the hierarchy. Here, we introduce the class of partitioned conditional generalized lin-ear models (PCGLMs) defined for an arbitrary number of levels. The hierarchical structure of these models is fully specified by a partition tree of categories. Using the genericity of the (r, F, Z) specification of GLMs for categorical data, PCGLMs can handle nominal, ordinal but also partially-ordered response variables.
Fichier principal
Vignette du fichier
PeyhardiTrottierGuedon2014b.pdf (472.21 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

hal-01084505 , version 1 (19-11-2014)

Identifiers

  • HAL Id : hal-01084505 , version 1
  • PRODINRA : 313847

Cite

Jean Peyhardi, Catherine Trottier, Yann Guédon. Partitioned conditional generalized linear models for categorical data. 29th International Workshop on Statistical Modelling (IWSM 2014), Statistical Modelling Society, Jul 2014, Göttingen, Germany. 4 p. ⟨hal-01084505⟩
371 View
234 Download

Share

Gmail Facebook X LinkedIn More