Individual level models vs. sample level models: contrasts and mutual benefits

With a view to better capturing heterogeneity across decision makers and improving prediction of choices, there is increasing interest in estimating separate models for each person. Almost exclusively, this work has however taken place outside the field of transport research. The aim of the present paper is twofold. The authors first wish to give an account of the potential benefits of a greater focus on individual level estimates in transport applications. Secondly, the authors wish to offer further insights into the relative benefits of sample level and individual level models (ILMs) by drawing on a data set containing an unusually large number (144) of decisions on holiday travel per individual. In addition to comparing existing approaches, the authors also put forward the use of a novel technique which draws on the relative benefits of both sample level and ILMs by estimating ILMs in a Bayesian fashion with priors drawn from a sample level model. The authors' results show only limited differences between ILMs and conditionals from sample level models when working with the full set of choices. When working with more realistic sample sizes at the person level, the authors' results suggest that ILMs can offer better performance on the estimation data but that this is a result of overfitting which can lead to inferior prediction performance. The authors' proposed Bayesian ILM model offers good intermediary performance. The use of best-worst data rather than simple stated choice, as is done commonly in published ILM work, does not lead to major changes to these findings.

• Record URL:
  • https://doi.org/10.1080/23249935.2015.1018681
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/23249935
• Supplemental Notes:
  • © 2015 Hong Kong Society for Transportation Studies Limited 2015. Abstract reprinted with permission of Elsevier.
• Authors:
  • Dumont, Jeffrey
  • Giergiczny, Marek
  • Hess, Stephane
• Publication Date: 2015-7

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 465-483
• Serial:
  • Transportmetrica A: Transport Science
  • Volume: 11
  • Issue Number: 6
  • Publisher: Taylor & Francis
  • ISSN: 2324-9935
  • EISSN: 2324-9943
  • Serial URL: http://www.tandfonline.com/loi/ttra21

Subject/Index Terms

• TRT Terms: Bayes' theorem; Choice models; Decision making; Mathematical prediction; Recreational trips; Statistical sampling
• Uncontrolled Terms: Heterogeneity (Choices); Sample sizes
• Subject Areas: Planning and Forecasting; Transportation (General); I72: Traffic and Transport Planning;

Filing Info

• Accession Number: 01561350
• Record Type: Publication
• Files: TRIS
• Created Date: Apr 27 2015 9:48AM