Household Vehicle Type Holdings and Usage: An Application of the Multiple Discrete-Continuous Extreme Value (mdcev) Model Chandra R. Bhat and Sudeshna Sen
Download 188.92 Kb.
|
- Navigate this page:
- Table 1. Vehicle Type Distribution of One – Vehicle Households
- Mean Annual Mileage (in miles)
- Table 2. Vehicle Type Distribution Among Two – Vehicle Households
- Percentage total number of two-vehicle household Mean Annual Mileage of vehicle type 1 (in miles)
- Table 3. Empirical Results
- Household sociodemographics
- Household location variables
- Baseline preference constants
- Table 4a. Satiation Parameters
- Table 4b. Variance-Covariance Matrix
- Table 5. Impact of an increase in operating (fuel) cost from $1.40 per gallon to $2.00 per gallon
- Percentage change in overall use of vehicle type
ACKNOWLEDGEMENTSThe authors would like to thank Chuck Purvis of the Metropolitan Transportation Commissions (MTC) in Oakland for providing help with data related issues. The authors also appreciate the valuable comments of an anonymous reviewer on an earlier version of the paper. REFERENCES Arora, N., G.M. Allenby, and J.L. Ginter (1998). A hierarchical Bayes model of primary and secondary demand. Marketing Science, 17, 29-44. Berkovec, J. (1985). Forecasting automobile demand using disaggregate choice models. Transportation Research Part B, 19(4), 315–329. Berkovec, J. and Rust, J. (1985). A nested logit model of automobile holdings for one vehicle households. Transportation Research Part B, 19(4), 275–285. Bhat, C.R. (1995). A Heteroscedastic Extreme Value Model of Intercity Mode Choice. Transportation Research Part B, 29(6), 471-483. Bhat, C.R. (2001). Quasi-Random Maximum Simulated Likelihood Estimation of the Mixed Multinomial Logit Model. Transportation Research Part B, 35(7), 677-693. Bhat, C.R. (2003). Simulation Estimation of Mixed Discrete Choice Models Using Randomized and Scrambled Halton Sequences. Transportation Research Part B, 37(9), 837-855. Bhat, C.R. (2005). A Multiple Discrete-Continuous Extreme Value Model: Formulation and Application to Discretionary Time-Use Decisions. In press, Transportation Research Part B. Birkeland, M.E. and Jordal-Jorgenson, J. (2001). Energy efficiency of passenger cars. Paper presented at the European Transport Conference 2001, PTRC, Cambridge, UK. Brownstone, D., Bunch, D., and Train, K. (2000). Joint mixed logit models of stated and revealed preferences for alternative-fuel vehicles, Transportation Research Part B: Methodological, 34(5), pp. 315–338. Bunch, D.S., Brownstone, D. and Golob, T.F. (1996). A dynamic forecasting system for vehicle markets with clean-fuel vehicles, World Transport Research, 1, pp. 189–203. Bunch, D.S. (2000). Automobile demand and type choice, in: D. A. Hensher and K. J. Button (Eds) Handbook of Transport Modelling, pp. 463–479 (Oxford: Pergamon). Chiang, J. (1991). A simultaneous approach to whether to buy, what to buy, and how much to buy. Marketing Science, 4, 297-314. Chintagunta, P.K. (1993). Investigating purchase incidence, brand choice and purchase quantity decisions of households. Marketing Science, 12, 194-208. Choo, S. and Mokhtarian, P.L. (2004). What type of vehicle do people drive? The role of attitude and lifestyle in influencing vehicle type choice. Transportation Research Part A, 38(3), 201–222. De Jong, G.C. (1996). A disaggregate model system of vehicle holding duration, type choice and use, Transportation Research Part B: Methodological, 30(4), pp. 263–276. De Jong, G.C., Fox, J., Daly, A., Pieters, M., and Smit, R. (2004) A comparison of car ownership models; Transport Reviews, Vol. 24, No. 4, 379-408. Dubin, J.A. and D.L. McFadden (1984). An econometric analysis of residential electric appliance holdings and consumption. Econometrica, 52(2), 345-362. Gilbert, C.S. (1992). A duration model of automobile ownership, Transportation Research Part B: Methodological, 26(2), pp. 97–114. HCG (1995). Further Development of a Dynamic Vehicle Transactions Model. Report 5037–1 (The Hague: Hague Consulting Group). Hannemann, M. (1984). The discrete/continuous model of consumer demand. Econometrica, 52, 541-561. Hausman, J.A. (1980). The effects of wages, taxes and fixed costs on women’s labor force participation; Journal of Public Economics 15, 161-194. Hensher, D.A., Barnard, P.O., Smith, N.C., and Milthorpe, F.W. (1992). Dimensions of automobile demand, A longitudinal study of automobile ownership and use, North-Holland, Amsterdam. Hocherman, I., Prashker, J.N. and Ben-Akiva, M. (1983). Estimation and use of dynamic transaction models of automobile ownership, Transportation Research Record, 944, pp. 134–141. Kim, J., Allenby, G.M., and Rossi, P.E. (2002). Modeling consumer demand for variety. Marketing Science, 21, 229-250. Kitamura, R., Golob, T.F., Yamamoto, T., Wu, G. (2000). Accessibility and auto use in a motorized metropolis. Paper presented at the 79th Transportation Research Board Annual Meeting, Washington, DC. Lave, C.A. and Train, K. (1979). A disaggregate model of auto-type choice. Transportation Research Part A, 13(1), 1–9. Mannering, F. and Winston, C. (1985). A dynamic empirical analysis of household vehicle ownership and utilization. Rand Journal of Economics, 16(2), 215–236. Mannering, F., Winston, C., Starkey, W. (2002). An exploratory analysis of automobile leasing by US households. Journal of Urban Economics, 52(1), 154–176. Manski, C.F. and Sherman, L. (1980). An empirical analysis of household choice among motor vehicles. Transportation Research Part A, 14(6), 349–366. Mohammadian, A. and Miller, E.J. (2003). An empirical investigation of household vehicle type choice decisions. Forthcoming, Transportation Research. Page, M., Whelan, G. and Daly, A. (2000). Modelling the factors which influence new car purchasing. Paper presented at the European Transport Conference 2000, PTRC, Cambridge, UK. Pucher, J. and Renne, J.L. (2003). Socioeconomics of urban travel: Evidence from 2001 NHTS. Transportation Quarterly, 57(3), 49-77. Train, K. (1986). Qualitative Choice Analysis: Theory, Econometrics and an Application to Automobile Demand (Cambridge, MA: MIT Press). Train, K. (2003). Discrete Choice Methods with Simulation. Cambridge University Press, Cambridge, United Kingdom. U.S. Environmental Protection Agency (EPA) and U.S. Department of Energy (DOE) (2004). Fuel Economy guide. Table 1. Vehicle Type Distribution of One – Vehicle Households
Table 2. Vehicle Type Distribution Among Two – Vehicle Households
* These numbers represents the mean total annual miles across both vehicles. Note that the annual mileage is computed for each vehicle type; in case both vehicles are of the same type, the entries correspond to the total miles across both vehicles. The numbers are the same across the “Mean annual mileage of vehicle type 1” and “Mean annual mileage of vehicle type 2” for this reason. Table 3. Empirical Results
Table 4a. Satiation Parameters
Table 4b. Variance-Covariance Matrix
Table 5. Impact of an increase in operating (fuel) cost from $1.40 per gallon to $2.00 per gallon
1A number of earlier studies have also focused on vehicle ownership levels and use. These studies are not of immediate interest here since the focus of the current paper is on vehicle type holdings and use. For a comprehensive review of studies on vehicle ownership/use (with no vehicle type holdings analysis), the reader is referred to De Jong et al., 2004. 2 Some studies, such as Train (1986), use the logarithm of vehicle use as the dependent variable. However, the basic functional relationship between the dependent and independent variables takes a linear regression form. 3Standard discrete choice models assume no satiation effects because they use a linear utility specification. That is, the marginal utility of any vehicle type is independent of vehicle usage. The reader is referred to Bhat, 2005 for further details. 4 The MMDCEV model used here is a static vehicle type holdings and use model, similar to the studies listed earlier in this section. Such static models predict holdings at any particular period without regard to the vehicle holdings in the earlier period. The application of such static models at different and closely-spaced time points can lead to the unrealistic situation of a household holding very different vehicle portfolios between the two time points. However, such static models may be reasonable over longer time periods, as indicated by De Jong et al. (2004). Another formulation that seeks to more consistently reflect the actual household vehicle holdings decision process is the dynamic vehicle transaction approach, in which households decide on disposing, adding, replacing, or maintaining the status quo of their current vehicles over time as well as the attributes of any new vehicles entering their household vehicle fleet (see, for example, Hocherman et al., 1983; Gilbert, 1992; HCG, 1995; De Jong, 1996; Bunch et al., 1996). The dynamic approach is particularly appealing for short-to-medium term forecasts. However, such transaction models require a “significant ongoing commitment to collecting panel data” (see Bunch, 2000) and can be relatively cumbersome to apply. Besides, the theoretical linkage between usage and vehicle type holdings is rather tenuous in most dynamic models to date. 5 This is only because we do not have adequate information from the survey to construct a mileage value for use of non-motorized modes of travel. If this information were available, we can add another “vehicle type” category corresponding to non-motorized modes. This category can be considered as an “outside good” which is always “consumed”, since households will use non-motorized modes for some amount of their travel (if at least for walking to the personal vehicle). In this instance, M would correspond to the total annual motorized and non-motorized travel mileage, and the annual motorized mileage would be endogenous to the model. The total annual motorized and non-motorized travel mileage would need to be modeled in an earlier step in this case. 6 The MDCEV model formulation also represents a multiple discrete-continuous extension of the single discrete-continuous model formulations of Hausman (1980), Dubin and McFadden (1984), Hanemann (1984), Mannering and Winston (1985), Train (1986), Chiang (1991), Chintagunta (1993), and Arora et al. (1998). In the single discrete-continuous models, the discrete alternatives are assumed to be perfect substitutes so that, in the context of the current application, only a single vehicle type is chosen. This may be viewed as a special two alternative case within the multiple discrete-continuous formulation, with one alternative (say the first) always being consumed. This first alternative may be labeled as “non-motorized travel mode”, an “outside good” which is always “consumed”, since households will use non-motorized modes for some amount of their travel (if at least for walking to the personal vehicle). The second alternative would be a composite of all motorized vehicle types, the baseline utility for which corresponds to the maximum utility across all motorized vehicle types j. This maximum utility is essentially a log-sum parameter from the standard discrete choice model for vehicle type. With this simplification, the MDCEV model is applicable to the single discrete-continuous case of a single vehicle type choice and corresponding usage. Of course, if the problem at hand is truly a single discrete-continuous one, the customized formulations of Hausman, Dubin and McFadden, Hanemann, and others listed above have the advantage of elegance and simplicity originating from the application of Roy’s identity to an indirect utility function that links the discrete and continuous choices. 7 The vehicle type classification used here is oriented toward transportation infrastructure planning and emissions modeling, and hence the detailed make/model of vehicles is not considered. Some earlier studies have used a finer definition of vehicle types to include vehicle makes and models (see Bunch, 2000 for a review). 8 The sample size of 3500 was based on run-time considerations as well as the judgment that 3500 observations were adequate for accurate and reliable model estimation. 9 As per the fuel economy statistics, passenger cars are considered the most fuel efficient vehicles, while pickup trucks and vans are considered the least fuel efficient. 10 An increase in vehicle operating costs would likely also impact other travel choices, such as travel mode and destination choice. These impacts are not modeled here. 11 As indicated in the footnote on page 8, the exogeneity of M is maintained because of data limitations. 12 The t-statistic is computed for the null hypothesis that the satiation parameter is equal to 1. Equivalently, the t-statistic is for the test that there are no satiation effects or that the utility structure is linear. Directory: prof -> bhat -> ABSTRACTS prof -> R institute of technology school of foreign languages prof -> Jackson State University Marching Band The Sonic Boom of the South prof -> The global aftershock zone prof -> Changsun Moon prof -> Michael Oudshoorn Contact Information ABSTRACTS -> The design of a comprehensive microsimulator of household vehicle fleet composition, utilization, and evolution ABSTRACTS -> Assessing the impact of urban form measures on nonwork trip mode choice after controlling for demographic and level-of-service effects Jayanthi Rajamani ABSTRACTS -> The Impact of Demographics, Built Environment Attributes, Vehicle Characteristics, and Gasoline Prices on Household Vehicle Holdings and Use Chandra R. Bhat Download 188.92 Kb. Share with your friends:
| |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||