Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

A Flexible Link Function for Discrete-Time Duration Models

Hess, Wolfgang LU ; Tutz, Gerhard and Gertheiss, Jan (2016) In Jahrbucher fur Nationalokonomie und Statistik 236(4). p.455-481
Abstract

This paper proposes a discrete-time hazard regression approach based on the relation between hazard rate models and excess over threshold models, which are frequently encountered in extreme value modelling. The proposed duration model employs a flexible link function and incorporates the grouped-duration analogue of the well-known Cox proportional hazards model and the proportional odds model as special cases. The theoretical setup of the model is motivated, and simulation results are reported, suggesting that the model proposed performs well. The simulation results and an empirical analysis of US import durations also show that the choice of link function in discrete hazard models has important implications for the estimation results,... (More)

This paper proposes a discrete-time hazard regression approach based on the relation between hazard rate models and excess over threshold models, which are frequently encountered in extreme value modelling. The proposed duration model employs a flexible link function and incorporates the grouped-duration analogue of the well-known Cox proportional hazards model and the proportional odds model as special cases. The theoretical setup of the model is motivated, and simulation results are reported, suggesting that the model proposed performs well. The simulation results and an empirical analysis of US import durations also show that the choice of link function in discrete hazard models has important implications for the estimation results, and that severe biases in the results can be avoided when using a flexible link function.

(Less)
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
discrete-time duration model, duration of trade, hazard rate, link function estimation, threshold excess model
in
Jahrbucher fur Nationalokonomie und Statistik
volume
236
issue
4
pages
27 pages
publisher
De Gruyter
external identifiers
  • scopus:84978884625
  • wos:000385014700002
ISSN
0021-4027
DOI
10.1515/jbnst-2015-1022
language
English
LU publication?
yes
id
d4a7dbb0-4726-4df7-8705-4514c87f24cb
date added to LUP
2016-12-14 12:03:17
date last changed
2024-06-28 21:40:10
@article{d4a7dbb0-4726-4df7-8705-4514c87f24cb,
  abstract     = {{<p>This paper proposes a discrete-time hazard regression approach based on the relation between hazard rate models and excess over threshold models, which are frequently encountered in extreme value modelling. The proposed duration model employs a flexible link function and incorporates the grouped-duration analogue of the well-known Cox proportional hazards model and the proportional odds model as special cases. The theoretical setup of the model is motivated, and simulation results are reported, suggesting that the model proposed performs well. The simulation results and an empirical analysis of US import durations also show that the choice of link function in discrete hazard models has important implications for the estimation results, and that severe biases in the results can be avoided when using a flexible link function.</p>}},
  author       = {{Hess, Wolfgang and Tutz, Gerhard and Gertheiss, Jan}},
  issn         = {{0021-4027}},
  keywords     = {{discrete-time duration model; duration of trade; hazard rate; link function estimation; threshold excess model}},
  language     = {{eng}},
  month        = {{08}},
  number       = {{4}},
  pages        = {{455--481}},
  publisher    = {{De Gruyter}},
  series       = {{Jahrbucher fur Nationalokonomie und Statistik}},
  title        = {{A Flexible Link Function for Discrete-Time Duration Models}},
  url          = {{http://dx.doi.org/10.1515/jbnst-2015-1022}},
  doi          = {{10.1515/jbnst-2015-1022}},
  volume       = {{236}},
  year         = {{2016}},
}