Competing-Risks-Duration Model of Household Vehicle Transactions with Indicators of Changes in Explanatory Variables

Abstract

A household-vehicle-transactions model that was developed as a competing-risks-duration model is presented. The model was developed assuming the following three types of competing risks: (a) replacing one of the vehicles in the household fleet, (b) disposing of one vehicle in the fleet, and (c) acquiring one vehicle to add to the fleet. In addition to the attributes of the household, changes in these attributes are expected to have strong effects on vehicle transaction behavior. To account for their effects, dummy variables indicating the occurrence of a change in selected household attributes were defined as time-varying covariates and introduced into the model. In addition, vehicle transactions themselves change the needs and motivations for vehicle holding, thus affecting the timing and the type of the transaction that immediately follows. Dummy variables indicating the type of the preceding transaction also were introduced as time-varying covariates into the model. The results of the empirical analysis using a data set collected in a panel survey empirically support the theoretical considerations underlying the model development and indicate that the effects of changes in household attributes and that of a preceding transaction are well represented in the model.

Get full access to this article

View all access options for this article.

References

Kitamura

Panel Analysis in Transportation Planning: An Overview. Transportation Research, Vol. 24A, No. 6, 1990, pp. 401–415.

Kitamura

A Review of Dynamic Vehicle Holdings Models and a Proposal for a Vehicle Transactions Model. Proc., Japan Society of Civil Engineers, No. 440/IV-16, Jan. 1992, pp. 13–29.

Kitamura

A Panel Analysis of Household Car Ownership and Mobility. Proc., Japan Society of Civil Engineers, No. 383/IV-7, July 1987, pp. 13–27.

Gilbert

C. C. S.

A Duration Model of Automobile Ownership. Transportation Research, Vol. 26B, No. 2, 1992, pp. 97–114.

de Jong

A Disaggregate Model System of Vehicle Holding Duration, Type Choice, and Use. Transportation Research, Vol. 30B, No. 4, 1996, pp. 263–276.

Yamamoto

, Matsuda

, and Kitamura

. An Analysis of Household Vehicle Holding Durations Relative to Intended Holding Durations (in Japanese). Infrastructure Planning Review, No. 14, 1997, pp. 799–808.

Yamamoto

, and Kitamura

. An Analysis of Household Vehicle Holding Durations Considering Intended Holding Durations. Presented at 8th Meeting of the International Association for Travel Behavior Research, Austin, Tex., 1997.

Hensher

The Timing of Change for Automobile Transactions: A Competing Risk Multispell Specification. Working paper, Institute of Transport Studies, University of Sydney, Australia, 1994.

Hensher

, and Mannering

. Hazard-Based Duration Models and Their Application to Transport Analysis. Transport Review, Vol. 14, No. 1, 1994, pp. 63–82.

10.

Han

, and Hausman

J. A.

. Flexible Parametric Estimation of Duration and Competing Risk Models. Journal of Applied Econometrics, Vol. 5, 1990, pp. 1–28.

11.

Bhat

C. R.

A Generalized Multiple-Duration Proportional Hazard Model with an Application to Activity Behavior During the Evening Work-to-Home Commute. Transportation Research, Vol. 30B, No. 6, 1996, pp. 465–480.

12.

Greene

W. H.

, and Econometric Software, Inc. LIMDEP Version 7.0 User’s Manual, Revised Edition. Econometric Software, Plainview, N.Y., 1998.

13.

Bunch

D. S.

, Brownstone

, and Golob

T. F.

. A Dynamic Forecasting System for Vehicle Markets with Clean-Fuel Vehicles. Proc., 7th World Conference on Transport Research, Pergamon, Oxford, England, 1995, pp. 189–203.

14.

Golob

T. F.

, Kim

, and Ren

. How Households Use Different Types of Vehicles: A Structural Driver Allocation and Usage Model. Transportation Research, Vol. 30A, No. 2, 1996, pp. 103–118.