A comparison of the predictive ability of mode choice models with various levels of complexity |
| |
| Affiliation: | 1. School of Traffic and Transportation, Beijing Jiaotong University, Haidian District, Beijing 100044, China;2. Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport, Beijing Jiaotong University, Haidian District, Beijing 100044, China;3. School of Engineering, Newcastle University, Newcastle Upon Tyne NE1 7RU, United Kingdom;4. Department of Transport and Planning, Delft University of Technology, Stevinweg 1, Delft, Netherlands;1. Beijing Key Laboratory of Traffic Engineering, Beijing University of Technology, Beijing, 100124, P.R. China;2. Key Laboratory of Advanced Public Transportation Sciences, Ministry of Transport, Beijing University of Technology, Beijing, 100124, P.R. China;3. Department of Civil and Environmental Engineering, the Hong Kong Polytechnic University, Hong Kong, P.R. China;1. Centre for Medicine Use and Safety, Faculty of Pharmacy and Pharmaceutical Sciences, Monash University, Parkville, Victoria, Australia;2. NHMRC Cognitive Decline Partnership Centre, Hornsby Ku-ring-gai Hospital, Hornsby, New South Wales, Australia;3. Department of Epidemiology and Preventive Medicine, Monash University, Melbourne, Victoria, Australia;4. Helping Hand Aged Care, North Adelaide, South Australia, Australia;5. Kolling Institute of Medical Research, Royal North Shore Hospital, Northern Clinical School, Faculty of Medicine and Health, University of Sydney, New South Wales, Australia;6. Centre for Health Services Research, The University of Queensland, Woolloogabba, Queensland, Australia;7. Drug & Therapeutics Information Service, GP Plus Marion, South Australia, Australia;8. Consumer Representative, Dementia Australia, Scullin, Australian Capital Territory, Australia;9. Helping Hand Consumer and Carer Reference Group, Helping Hand Aged Care, North Adelaide, South Australia, Australia;1. Agricultural Economics, Research Faculty of Agriculture, Hokkaido University, Kita-9, Nish-9, Kita-ku, Sapporo, Hokkaido, 060-8589, Japan;2. Agricultural and Resource Economics, School of Agriculture and Environment, The University of Western Australia, 35 Stirling Highway, Perth, 6009, Western Australia, Australia;1. SWOV Institute for Road Safety Research, P.O. Box 93113, 2509 AC The Hague, the Netherlands;2. Transport and Mobility Laboratory, School of Architecture, Civil and Environmental Engineering, École Polytechnique Fédérale de Lausanne, Station 18, 1015 Lausanne, Switzerland |
| |
| Abstract: | Models of mode choice have recently been developed which include a large number of explanatory variables. The inclusion of some of these variables is obviously the result of trial-and-error analysis of various model specifications: the researcher tries various specifications until he obtains a specification which is consistent with a priori beliefs and fits the data fairly well. This method of model specification allows one to “learn” from the data, but is also open to the critism that the resultant model simply reflects relations which happen to exist in the sample, rather than true, behavioral relations.This paper examines this question. A complex model is presented which was developed after attempting a wide variety of specifications. The predictive ability of this model is compared with that of models with fewer variables, each of which could be included on the basis of a priori ideas. It is found that the complex model predicts best, indicating that the behavioral content of the model which was developed through “learning” from the data is greater than that of models which were specified on a priori beliefs. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
