Ordered regression models. Parallel, partial, and non-parallel alternatives (Q2799455)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 6567072
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Ordered regression models. Parallel, partial, and non-parallel alternatives |
scientific article; zbMATH DE number 6567072 |
Statements
11 April 2016
0 references
ordered regression
0 references
ordinal dispersion
0 references
heterogeneous choice models
0 references
logit
0 references
probit
0 references
loglog models
0 references
information measures
0 references
Bayesian approach
0 references
Ordered regression models. Parallel, partial, and non-parallel alternatives (English)
0 references
This book presents a comprehensive coverage of ordered regression models divided into three classes: cumulative, stage and adjacent models. Properties of each of these classes are highlighted in applications to examples of self health evaluation, educational attainment and attitudes toward welfare spending, respectively. Parallel, partial and nonparallel formulations are separately studied. The use of logit, probit and complementary loglog link functions is compared. Relaxation of independence and homoscedasticity assumptions is considered. Tests for the parallel regression assumption are discussed, as well as the use of information measures and marginal effects to compare the relative fit of different models. A Bayesian approach is also developed. Stata and R codes are provided for different models.
0 references
0.739052414894104
0 references
0.7376532554626465
0 references
0.7362257242202759
0 references
0.7362257242202759
0 references
