A Note On Generalized Ordered Outcome Models
Keywords
Generalized Ordered Logit; Ordered discrete outcome models; Ordinal discrete variables; Partial proportional odds model; Transportation safety; Unobserved heterogeneity
Abstract
While there is growing application of generalized ordered outcome model variants (widely known as Generalized Ordered Logit (GOL) model and Partial Proportional Odds Logit (PPO) model) in crash injury severity analysis, there are several aspects of these approaches that are not well documented in extant safety literature. The current research note presents the relationship between these two variants of generalized ordered outcome models and elaborates on model interpretation issues. While these variants arise from different mathematical approaches employed to enhance the traditional ordered outcome model, we establish that these are mathematically identical. We also discuss how one can facilitate estimation and interpretation while building on the ordered outcome model estimates - a useful process for practitioners considering upgrading their existing traditional ordered logit/probit injury severity models. Finally, the note presents the differences within GOL and PPO model frameworks, for accommodating the effect of unobserved heterogeneity, referred to as Mixed Generalized Ordered Logit (MGOL) and Mixed Partial Proportional Odds Logit (MPPO) models while also discussing the computational difficulties that may arise in estimating these models.
Publication Date
12-29-2015
Publication Title
Analytic Methods in Accident Research
Volume
8
Number of Pages
1-6
Document Type
Article
Personal Identifier
scopus
DOI Link
https://doi.org/10.1016/j.amar.2015.04.002
Copyright Status
Unknown
Socpus ID
84940477104 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84940477104
STARS Citation
Eluru, Naveen and Yasmin, Shamsunnahar, "A Note On Generalized Ordered Outcome Models" (2015). Scopus Export 2015-2019. 6.
https://stars.library.ucf.edu/scopus2015/6