David S. Bunch

Hybrid Choice Models: Progress and Challenges

We discuss the development of predictive choice models that go beyond the random utility model in its narrowest formulation. Such approaches incorporate several elements of cognitive process that have been identified as important to the choice process, including strong dependence on history and context, perception formation, and latent constraints. A flexible and practical hybrid choice model is presented that integrates many types of discrete choice modeling methods, draws on different types of data, and allows for flexible disturbances and explicit modeling of latent psychological explanatory variables, heterogeneity, and latent segmentation. Both progress and challenges related to the development of the hybrid choice model are presented.

Demand for clean-fuel vehicles in California: A discrete-choice stated preference pilot project

A study was conducted to determine how demand for clean-fuel vehicles and their fuel is likely to vary as a function of attributes that distinguish these vehicles from conventional gasoline vehicles. For the purposes of the study, clean-fuel vehicles are defined to encompass both electric vehicles and unspecified (methanol, ethanol, compressed natural gas or propane) liquid and gaseous fuel vehicles, in both dedicated or multiple-fuel versions. The attributes include vehicle purchase price, fuel operating cost, vehicle range between refueling, availability of fuel, dedicated versus multiple-fuel capability and the level of reduction in emissions (compared to current vehicles). In a mail-back stated preference survey, approximately 700 respondents in the California South Coast Air Basin gave their choices among sets of hypothetical future vehicles, as well as their choices between alternative fuel versus gasoline for hypothetical multiple-fuel vehicles. Estimates of attribute importance and segment differences are made using discrete-choice nested multinomial logit models for vehicle choice and binomial logit models for fuel choice. These estimates can be used to modify present vehicle-type choice and utilization models to accomodate clean-fuel vehicles; they can also be used to evaluate scenarios for alternative clean-fuel vehicle and fuel supply configurations. Results indicate that range between refueling is an important attribute, particularly if range for an alternative fuel is substantially less than that for gasoline. For fuel choice, the most important attributes are range and fuel cost, but the predicted probability of choosing alternative fuel is also affected by emissions levels, which can compensate for differences in fuel prices.

ESTIMABILITY IN THE MULTINOMIAL PROBIT MODEL

Random utility models often involve terms which represent alternative-specific errors, and the main attractive feature of the multinomial probit (MNP) model is that it allows a rather general covariance structure for these errors. However, since observed choices only reveal information regarding utility differences, and since scale cannot be determined, not all parameters in an arbitrary MNP specification may be identified. This paper examines identification restrictions that arise in the linear-in-parameters multinomial probit framework, and provides discussion and recommendations for estimation and analysis of probit normalizations.

The American Put Option and Its Critical Stock Price

We derive an expression for the critical stock price for the American put. We start by expressing the put price as an integral involving first-passage probabilities. This approach yields intuition for Mertons result for the perpetual put. We then consider the finite-lived case. Using (1) the fact that the put value ceases to depend on time when the critical stock price is reached and (2) the result that an American put equals a European put plus an early-exercise premium, we derive the critical stock price. We approximate the critical-stock-price function to compute accurate put prices. Copyright The American Finance Association 2000.

A transactions choice model for forecasting demand for alternative-fuel vehicles

The vehicle choice model developed here is one component in a micro-simulation demand forecasting system being designed to produce annual forecasts of new and used vehicle demand by vehicle type and geographic area in California. The system will also forecast annual vehicle miles traveled for all vehicles and recharging demand by time of day for electric vehicles. The choice model specification differs from past studies by directly modeling vehicle transactions rather than vehicle holdings. The model is calibrated using stated preference data from a new study of 4,747 urban California households. These results are potentially useful to public transportation and energy agencies in their evaluation of alternatives to current gasoline-powered vehicles. The findings are also useful to manufacturers faced with designing and marketing alternative-fuel vehicles as well as to utility companies who need to develop long-run demand-side management planning strategies.

Who Deters Entry? Evidence on the Use of Strategic Entry Deterrents

To deter entry into new product markets, firms most often use the creation of product loyalty through advertising and the preemption of markets through numerous and broad patents. Filling all product niches, making the results for highly profitable division, and advertising are used most frequently for existing products. For newly developed products, strategic entry deterrents are used more often when markets are concentrated, populated by large firms, and research intensive. Strategic entry deterrents for existing products are used in concentrated, research intensive markets, but firm size has no effect. Firms develop strategies to deter entry less when other barriers exist. Copyright 1992 by MIT Press.

Combining Sources of Preference Data for Modeling Complex Decision Processes

We review current state-of-the-art practices for combining preference data from multiple sources and discuss future research possibilities. A central theme is that any one data source (e.g., a scanner panel source) is often insufficient to support tests of complex theories of choice and decision making. Hence, analysts may need to embrace a wider variety of data types and measurement tools than traditionally have been considered in applied decision making and choice research. We discuss the viability of preference-stationarity assumptions usually made when pooling data, as well as random-utility theory-based approaches for combining data sources. We also discuss types of models and data sources likely to be required to make inferences about and estimate models that describe choice dynamics. The latter discussion is speculative insofar as the body of literature on this topic is small.

Optimal Designs for 2k Paired Comparison Experiments

In this paper we establish the form of the optimal paired comparison design when there are k attributes, each with two levels, for testing for main effects, for main effects and two factor interactions and for main effects and two and three factor interactions. In all cases we assume that all pairs with the same number of attributes different appear equally often. In this setting the D and A optimal designs for main effects are the foldover pairs and those for main effects and two factor interactions have pairs in which about half the attributes are different.

Algorithm 717: Subroutines for maximum likelihood and quasi-likelihood estimation of parameters in nonlinear regression models

We present FORTRAN 77 subroutines that solve statistical parameter estimation problems for general nonlinear models, e.g., nonlinear least-squares, maximum likelihood, maximum quasi-likelihood, generalized nonlinear least-squares, and some robust fitting problems. The accompanying test examples include members of the generalized linear model family, extensions using nonlinear predictors (“nonlinear GLIM”), and probabilistic choice models, such as linear-in-parameter multinomial probit models. The basic method, a generalization of the NL2SOL algorithm for nonlinear least-squares, employs a model/trust-region scheme for computing trial steps, exploits special structure by maintaining a secant approximation to the second-order part of the Hessian, and adaptively switches between a Gauss-Newton and an augmented Hessian approximation. Gauss-Newton steps are computed using a corrected seminormal equations approach. The subroutines include variants that handle simple bounds on the parameters, and that compute approximate regression diagnostics.

Predicting the market penetration of electric and clean-fuel vehicles

Abstract Air quality in Southern California and elsewhere could be substantially improved if some gasoline-powered personal vehicles were replaced by vehicles powered by electricity or alternative fuels, such as methanol, ethanol, propane, or compressed natural gas. Quantitative market research information about how consumers are likely to respond to alternative-fuel vehicles is critical to the development of policies aimed at encouraging such technological change. In 1991, a three-phase stated preference (SP) survey was implemented in the South Coast Air Basin of California to predict the effect on personal vehicle purchases of attributes that potentially differentiate clean-fuel vehicles from conventional gasoline (or diesel) vehicles. These attributes included: limited availability of refueling stations, limited range between refueling or recharging, vehicle prices, fuel operating costs, emissions levels, multiple-fuel capability and performance. Respondents were asked to choose one vehicle from each of five sets of hypothetical clean-fuel and conventional gasoline vehicles, each vehicle defined in terms of attributes manipulated according to a specific experimental design. Discrete choice models, such as the multinominal logit model, are then used to estimate how the values of the attribute levels influence purchase decisions. The SP survey choice sets were customized to each respondents situation, as determined in the preceding phase of the survey. The final phase of the survey involved fuel-choice SP tasks for multi-fuel vehicles that can run on either clean fuels or gasoline. Preliminary results from a pilot sample indicate that the survey responses are plausible and will indeed be useful for forecasting.