Factors affecting hospital stay involving drunk driving and non-drunk driving in Phuket, Thailand
The purpose of this paper is to investigate the factors affecting hospital stay involving drunk driving and non-drunk driving of accident victims in Phuket, Thailand. However, the decisions to drink and drive are made by the road users before the accidents occurred. Self-selection bias may arise whe...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
Springer Verlag
2014
|
| Online Access: | http://www.scopus.com/inward/record.url?eid=2-s2.0-84897835778&partnerID=40&md5=6327f2244e2a89690261bef1eb0e2463 http://cmuir.cmu.ac.th/handle/6653943832/1194 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Chiang Mai University |
| Language: | English |
| Summary: | The purpose of this paper is to investigate the factors affecting hospital stay involving drunk driving and non-drunk driving of accident victims in Phuket, Thailand. However, the decisions to drink and drive are made by the road users before the accidents occurred. Self-selection bias may arise when some component of the drink and drive decision is relevant to the length of stay in hospital of accident victims. We discuss a new approach to specifying and estimating zero-inflated negative binomial models with endogenous switching, based on copula function. These models provide a framework of analysis for the effect of self-selection in drunk-driving behaviors on the length of stay in the hospitals. We use the concept of pair-copula constructions for discrete margins to derive the likelihood function of our model system. The results suggest that drunk-driving accident victims are positively selected. © Springer International Publishing Switzerland 2014. |
|---|