A simulation evaluation of the maximum approximate composite marginal likelihood (MACML) estimator for mixed multinomial probit models

This paper evaluates the ability of the maximum approximate composite marginal likelihood (MACML) estimation approach to recover parameters from finite samples in mixed cross-sectional and panel multinomial probit models. Comparisons with the maximum simulated likelihood (MSL) estimation approach are also undertaken. The results indicate that the MACML approach recovers parameters much more accurately than the MSL approach in all model structures and covariance specifications. The MACML inference approach also estimates the parameters efficiently, with the asymptotic standard errors being, in general, only a small proportion of the true values. As importantly, the MACML inference approach takes only a very small fraction of the time needed for MSL estimation. In particular, the results suggest that, for the case of five random coefficients, the MACML approach is about 50 times faster than the MSL for the cross-sectional random coefficients case, about 15 times faster than the MSL for the panel inter-individual random coefficients case, and about 350 times or more faster than the MSL for the panel intra- and inter-individual random coefficients case. As the number of alternatives in the unordered-response model increases, one can expect even higher computational efficiency factors for the MACML over the MSL approach. Further, as should be evident in the panel intra- and inter-individual random coefficients case, the MSL is all but practically infeasible when the mixing structure leads to an explosion in the dimensionality of integration in the likelihood function, but these situations are handled with ease in the MACML approach. It is hoped that the MACML procedure will spawn empirical research into rich model specifications within the context of unordered multinomial choice modeling, including autoregressive random coefficients, dynamics in coefficients, space-time effects, and spatial/social interactions.     

Air itinerary shares estimation using multinomial logit models

ABSTRACT

The main goal of this study is the development of an aggregate air itinerary market share model. In order to achieve this, multinomial logit models are applied to distribute the city-pair passenger demand across the available itineraries. The models are developed at an aggregate level using open-source booking data for a large group of city-pairs within the US air transport system. Although there is a growing trend in the use of discrete choice models in the aviation industry, existing air itinerary share models are mostly focused on supporting carrier decision-making. Consequently, those studies define itineraries at a more disaggregate level using variables describing airlines and time preferences. In this study, we define itineraries at a more aggregate level, i.e. as a combination of flight segments between an origin and destination, without further insight into service preferences. Although results show some potential for this approach, there are challenges associated with prediction performance and computational intensity.     

The maximum approximate composite marginal likelihood (MACML) estimation of multinomial probit-based unordered response choice models

The likelihood functions of multinomial probit (MNP)-based choice models entail the evaluation of analytically-intractable integrals. As a result, such models are usually estimated using maximum simulated likelihood (MSL) techniques. Unfortunately, for many practical situations, the computational cost to ensure good asymptotic MSL estimator properties can be prohibitive and practically infeasible as the number of dimensions of integration rises. In this paper, we introduce a maximum approximate composite marginal likelihood (MACML) estimation approach for MNP models that can be applied using simple optimization software for likelihood estimation. It also represents a conceptually and pedagogically simpler procedure relative to simulation techniques, and has the advantage of substantial computational time efficiency relative to the MSL approach. The paper provides a “blueprint” for the MACML estimation for a wide variety of MNP models.     

Bayesian updating of trip generation data: Combining national trip generation rates with local data

With traffic impact analyses and impact fee assessment becoming more popular, the need for accurately estimating the trip generation rate of a proposed development is becoming more important. An overwhelming percentage of state transportation agencies depend either partly or entirely on the ITETrip Generation Report to predict the traffic that will be attracted to and/or produced from a proposed development. However, the rates obtained from the ITE publication have been derived from data collected throughout the United States. They represent a national average and fail to take into account the local trip generation characteristics that the site under consideration might have. This paper establishes a methodology for obtaining more reliable local trip generation rates using Bayesian statistics. In this method, the ITE rates are assumed to be the prior information, which are updated using limited local trip generation data that are available. The method also allows for temporal updating, incorporating subjective judgment and using borrowed data in the updating procedure. Sample calculations in this paper illustrate the developed methodology.     

Comparison of updating techniques in transferability analysis of work trip mode choice models in developing countries

This study analyzes the performances of updating techniques in transferability of mode choice models in developing countries. A model specification, estimated in Ho Chi Minh City, was transferred to Phnom Penh. Naïve transfer and four updating methods associated with small sized samples were used in the transfer process and were evaluated based on statistical perspective and predictive ability. The study also illustrates the problems faced in model transferability development, due to the lack of available and suitable data in Phnom Penh. This lack is strongly related to different methods and structures applied in collecting the data. Simplified approaches to the difficulties are proposed in the study. The results show that updating ASCs, updating both ASCs and scale parameter, and use of combined transfer estimators all produce significant improvement, both statistically and in predictability, in updating the model. The last two methods have proven to be superior to the first method, owing to the inclusion of transfer bias considerations in the estimations. However, small data samples should not have large transfer bias when using combined transfer estimators. It is also concluded that naïvely transferring a model is not recommended, and Bayesian updating should be avoided when transfer bias exists. Copyright © 2010 John Wiley & Sons, Ltd.     

Implicit choice set generation in discrete choice models: Application to household auto ownership decisions

Latent choice set models that account for probabilistic consideration of choice alternatives during decision making have long existed. The Manski model that assumes a two-stage representation of decision making has served as the standard workhorse model for discrete choice modeling with latent choice sets. However, estimation of the Manski model is not always feasible because evaluation of the likelihood function in the Manski model requires enumeration of all possible choice sets leading to explosion for moderate and large choice sets. In this study, we propose a new group of implicit choice set generation models that can approximate the Manski model while retaining linear complexity with respect to the choice set size. We examined the performance of the models proposed in this study using synthetic data. The simulation results indicate that the approximations proposed in this study perform considerably well in terms of replicating the Manski model parameters. We subsequently used these implicit choice set models to understand latent choice set considerations in household auto ownership decisions of resident population in the Southern California region. The empirical results confirm our hypothesis that certain segments of households may only consider a subset of auto ownership levels while making decisions regarding the number of cars to own. The results not only underscore the importance of using latent choice models for modeling household auto ownership decisions but also demonstrate the applicability of the approximations proposed in this study to estimate these latent choice set models.     

Analysis of parking cruising behaviour and parking location choice

ABSTRACT

This paper explores car drivers’ cruising behaviour and location choice for curb parking in areas with insufficient parking space based on a survey of car drivers in Beijing, China. Preliminary analysis of the data show that car drivers’ cruising behaviour is closely related to their parking duration and parking location. A multinomial probit (MNP) model is used to analyse cruising behaviour and the results show that the closer to the destination car drivers are, the more likely they choose to park on the curb. The adjacent locations are the basis of car drivers’ sequential parking decisions at different locations. The research results provide a better understanding of cruising behaviour for parking and recommendations for reducing cruising for parking. The provision of parking information can help regulate the parking demand distribution.     

Comparative analysis of traveler destination choice models by method of sampling alternatives

In a destination choice model, it is important to introduce alternatives that have been adequately aggregated into traffic analysis zone levels based on spatial similarities and feasibility of analysis, because considering every spatial location possible for the traveler as an elemental alternative is intractable in terms of data management and analysis. In this study, we derive strata for alternative sets through simple random sampling and stratified importance sampling based on the concept of Moran’s I. As a result of comparative analysis, we are able to reduce errors by drawing an adequate number of samples for the destination choice model’s choice alternative sets based on measures of spatial similarity.     

Formulating a methodology for modelling revealed preference discrete choice data-the selectively replicated logit estimation

There are a number of studies on modelling with Revealed Preference (RP) data. It is a traditional technique and it is based on actual market data. The method has been extensively used in transportation as a tool for predicting travel demand. Although the method constitutes a relevant analysis on the process of modelling, it suffers from limitations, mainly associated with the lack of control over the experiment, that sometimes overwhelm the model results. This work proposes and tests a methodology for estimating a more efficient binary RP sample set. The objective is to develop and test a methodology that identifies and eliminates potentially irrational choices made. Responses are evaluated according to the set of trade-offs in values of time. Having identified these individuals they are eliminated from the original sample and a new sample is created, the selectively replicated (SR) sample. Original and SR samples are then re-estimated in a tree nested logit structure.     

Introducing non-normality of latent psychological constructs in choice modeling with an application to bicyclist route choice

In the current paper, we propose the use of a multivariate skew-normal (MSN) distribution function for the latent psychological constructs within the context of an integrated choice and latent variable (ICLV) model system. The multivariate skew-normal (MSN) distribution that we use is tractable, parsimonious in parameters that regulate the distribution and its skewness, and includes the normal distribution as a special interior point case (this allows for testing with the traditional ICLV model). Our procedure to accommodate non-normality in the psychological constructs exploits the latent factor structure of the ICLV model, and is a flexible, yet very efficient approach (through dimension-reduction) to accommodate a multivariate non-normal structure across all indicator and outcome variables in a multivariate system through the specification of a much lower-dimensional multivariate skew-normal distribution for the structural errors. Taste variations (i.e., heterogeneity in sensitivity to response variables) can also be introduced efficiently and in a non-normal fashion through interactions of explanatory variables with the latent variables. The resulting model we develop is suitable for estimation using Bhat’s (2011) maximum approximate composite marginal likelihood (MACML) inference approach. The proposed model is applied to model bicyclists’ route choice behavior using a web-based survey of Texas bicyclists. The results reveal evidence for non-normality in the latent constructs. From a substantive point of view, the results suggest that the most unattractive features of a bicycle route are long travel times (for commuters), heavy motorized traffic volume, absence of a continuous bicycle facility, and high parking occupancy rates and long lengths of parking zones along the route.     

Bayesian imputation of non‐chosen attribute values in revealed preference surveys

Obtaining attribute values of non‐chosen alternatives in a revealed preference context is challenging because non‐chosen alternative attributes are unobserved by choosers, chooser perceptions of attribute values may not reflect reality, existing methods for imputing these values suffer from shortcomings, and obtaining non‐chosen attribute values is resource intensive. This paper presents a unique Bayesian (multiple) Imputation Multinomial Logit model that imputes unobserved travel times and distances of non‐chosen travel modes based on random draws from the conditional posterior distribution of missing values. The calibrated Bayesian (multiple) Imputation Multinomial Logit model imputes non‐chosen time and distance values that convincingly replicate observed choice behavior. Although network skims were used for calibration, more realistic data such as supplemental geographically referenced surveys or stated preference data may be preferred. The model is ideally suited for imputing variation in intrazonal non‐chosen mode attributes and for assessing the marginal impacts of travel policies, programs, or prices within traffic analysis zones. Copyright © 2012 John Wiley & Sons, Ltd.     

An exploration of shoppers travel mode choice in visiting convenience stores in the UK

Using data from over 2000 convenience store customers within and outside London, this paper explores how individuals access their convenience stores and how significant the influence of their socio-demographics, shopping types and trip chaining is to their mode choice in visiting the stores. Trip chaining is found to be crucial in influencing customers' mode choice and their visit frequency. The application of logit models also shows that frequent shoppers are the ones most likely to visit the stores on foot. Interestingly, the estimation results also show that the location's density, shopping types and the day of the week are not significant in influencing travel modes. Customers who live in the most deprived areas are less likely to use a private car in visiting the stores.     

A comparative study of aggregate and disaggregate gravity models using Seoul metropolitan subway trip data

Abstract

Existing origin constrained and doubly constrained gravity models have not been compared, theoretically or empirically, in terms of their forecasting power. Due to the newly advanced technology of intelligent transport systems, the expanded data presently available have made various models more comparable in terms of forecasting power. This paper uses archived automatic passenger counting (APC) data for urban rail in the Seoul metropolitan area. The APC data contains information about each trip's origin, destination, ticket type, fare, and distance on a daily basis. The objective of this paper is to compare the goodness-of-fit of aggregate and disaggregate gravity modeling using these data. A Hyman aggregate gravity model is used as the aggregate model without the spatial effect. The disaggregate model adopts a multinomial logit as the destination choice model with the spatial effect. In general, while the formulation of aggregate and disaggregate gravity model models are similar, the calibration and parameter estimation methods of the two models are different. As a result, this empirical study demonstrates that the variation in goodness-of-fit and forecasting power largely depends on the estimation method and selected variables. The forecasting power of the disaggregate modeling approach outperforms that of the aggregate model. This paper further confirms that spatial arrangement plays important roles in gravity modeling.     

A comparative study of a hybrid Logit–Fratar and neural network models for trip distribution: case of the city of Isfahan

This paper introduces a new procedure to forecast the future O/D demand. It is a hybrid of logit and Fratar model. The hybrid model has the long run, policy sensitive, characteristic of a logit model, calibrated at sector‐level with little/no zero O/D cells. This feature, joint with a Fratar‐type operation at zonal level within a sector, gives a better performance to this model than either of the two types of the models alone. The performance of the hybrid model is contrasted with a neural network model, and shows encouraging results in a real case. Copyright © 2010 John Wiley & Sons, Ltd.     

Expanding scope of hybrid choice models allowing for mixture of social influences and latent attitudes: Application to intended purchase of electric cars

Recently, policy makers’ expectations about the role of electric cars in reducing emissions have risen substantially. In parallel, academic research on purchase intentions has dramatically increased. Originally, most studies have focused on utility attributes and price. More recently, several hybrid choice models have been estimated to include the impact of attitudes on choice probabilities. In addition, a few studies have caught the attention to social influence. In contributing to this line of research, this paper reports the results of an expanded hybrid choice, which simultaneously estimated all these different effects in a single integrated model of purchase intention. Results indicate that the model performs well. Costs considerations contribute most to the utility of electric cars. Social influence is less important, but there is also evidence that people tend to take it into consideration when there are positive public opinions about electric cars and the market share becomes almost half of friends of their social network. The intention to purchase an electric car is also influenced by attitudes about environmental concerns and technology acceptance.     

Estimating heterogeneity of car travelers on mode shifting behavior based on discrete choice models

In order to understand the mode shift behavior of car travelers and relieve traffic congestion, a Stated Preference survey has been conducted in the city of Ji'nan in China to analyze bus choice behavior and the heterogeneity of car travelers. Several discrete choice models, including multinomial logit, mixed logit and latent class model (LCM) are developed based on these survey data. A comparative analysis indicates that the LCM has the highest precision and is more suitable to analyze the heterogeneity of car travelers. The LCM divides car travelers into three classes. Different classes have different sets of influencing factors in the model. Policy recommendations are also proposed for those classes to promote bus shift from car travelers based on the model results. Finally, sensitivity analysis on parking fees and fuel cost is carried out on the LCMs under different bus service levels. Car travelers have different sensitivities to the influencing factors. The conclusions indicate that the LCM can reflect the heterogeneity and preferences of car travelers and can be used to understand how to shift the behavior of car travelers and make more effective traffic policy.