Journal of Choice Modelling最新文献

Taking a holiday trip is a common couple-based leisure activity in which both partners tend to be actively involved. This paper studies the intra-household bargaining for the choice of a vacation destination within couples. We conduct a discrete choice experiment in which we elicit both individual and couple preferences for different hypothetical travel portfolios in a two-stage experimental design. The couple choices are modelled as a function of males' and females' individual preferences, allowing for different bargaining weights for each characteristic of the holiday trip. Therefore, we assess partners’ bargaining power (influence) in the couple choices conditional on individual preferences. We find that although males have a more influential role overall, there seems to be a gender specialization in that females decide on the type of accommodation and males focus on the trip cost.

Individual migration mobilities over the life course have not been well understood in existing studies, and therefore ways to represent the underlying intertemporal dynamics and heterogeneities have remained unclear. To fill this research gap, this study investigates the domestic migration of people residing in the Capital Area of Japan, which has suffered from various issues caused by the over-concentration of population for several decades. Using a web-based questionnaire survey, workers aged 20–49 living in the Capital Area were requested to recall their five latest migration experiences (i.e., migration biography). A life-course intertemporal discrete choice model with cross-sectional and longitudinal heterogeneities was developed to represent individual migration destination biographies, by introducing quasi-hyperbolic utility and drawing on time preference theory. It was found that a considerable proportion of working people in the Capital Area (especially Tokyo) are from other regions of Japan. In the modeling analysis, the temporally-changing, intertwined and heterogeneous roles of place attachment, motives and altruism in migration decisions over the life course are empirically confirmed. Nonlinear influences of past, present and future utilities are further revealed, where the past utility grows more influential, and the importance of future utility diminishes over time. Policy implications of the derived findings for the development of megacities and local cities are discussed.

An important component of the design phase of a discrete choice experiment (DCE) is formulating the cost vector, which specifies the costs of the alternatives and enables the calculation of marginal willingness to pay (WTP) estimates. If the cost vector affects choice behaviour, welfare estimates may depend on the choice of the cost vector, which leads to problems with the validity and reliability of DCE results. We employ a split-sample design to examine cost vector effects on choice behaviour and WTP estimates. Our data come from a DCE on agri-environmental policies to a nationally representative sample in Finland. We provide additional insights compared to previous research by including four cost vectors with otherwise identical surveys and experimental designs and a positive cost for the status quo alternative, with cost levels for policy alternatives both below and above the status quo cost. We obtain some evidence that the cost vector affects choice behaviour, as the proportion of status quo choices is larger with higher cost vectors. Both absolute and relative cost levels matter for choices. The marginal WTP estimates are highest in the sub-sample with the largest range cost vector that has cost levels both below and above the status quo cost. We suggest more careful pre-testing of the cost levels compared to current practices to determine a plausible range of cost levels to produce valid welfare estimates.

We propose three procedures based on association rules (AR) learning and random forests (RF) to support the specification of a portfolio choice model applied in data from complex choice experiment data, specifically a Participatory Value Evaluation (PVE) choice experiment. In a PVE choice experiment, respondents choose a combination of alternatives, subject to a resource constraint. We combine a methodological-iterative (MI) procedure with AR learning and RF models to support the specification of parameters of a portfolio choice model. Additionally, we use RF model predictions to contrast the validity of the behavioural assumptions of different specifications of the portfolio choice model. We use data of a PVE choice experiment conducted to elicit the preferences of Dutch citizens for lifting COVID-19 measures. Our results show model fit and interpretation improvements in the portfolio choice model, compared with conventional model specifications. Additionally, we provide guidelines on the use of outcomes from AR learning and RF models from a choice modelling perspective.

This article investigates the usage of a general model-based recursive partitioning algorithm to model preference heterogeneity. We use the algorithm to grow a decision tree based on statistical tests of the stability of individuals’ preference parameters. In particular, we used a Mixed Logit (MIXL) model with alternative-specific attributes at the end leaves of the tree while using individual characteristics as partition variables. This configuration allows us to search for instabilities of the taste parameters across individuals’ characteristics. We conduct a simulation study to investigate the algorithm’s ability to recover different data generating processes with structural breaks in the taste parameters. The results show that the algorithm can correctly recover diverse tree-like data generating processes. Additionally, we applied the algorithm to stated choice data of the preferences for the environmental impact of (hypothetical) energy generation plans in Chile. The results show that the model-based decision tree fits the data better than MIXL in terms of information criteria. Moreover, we show that the derived tree structure depends on the assumptions on the parameters’ distributions. Additionally, we compare the model-based decision tree model with Latent Class (LC) models with and without within-class heterogeneity. Finally, we show that the recursive partitioning algorithm can inform the selection of variables to be included in the LC allocation models.

This paper presents a random utility maximization model for individuals selecting discrete quantities from a set of n alternatives. Multiple alternatives with positive quantities may be selected. Diminishing marginal utility to quantity of each alternative is modeled via order statistics of independent Gumbel random variables. The model is parsimonious and tractable, admitting closed-form expressions for choice probabilities. As such, the model is amenable to maximum likelihood estimation of structural parameters from observed choices.

Probability functions recover binary logit probabilities under binary choice and a maximum quantity of one unit, and probability is monotonic in the quantity of each alternative. The monotonic property likely restricts the application of the model to a narrow range of settings. The property is a manifestation of a recursive relationship among Gumbel order statistic probabilities. This relationship and related properties may lead to new models for capturing important complexities in a tractable manner.

Endogeneity and correlated alternatives are major concerns to be addressed in travel behavior analysis. However, these issues have rarely been dealt with simultaneously in advanced discrete choice models. This study proposes a multinomial probit model that incorporates the instrumental variable method, namely, a fully parametric instrumental variable model for a multinomial choice. The proposed model has the following three characteristics: (1) it allows binary and/or continuous endogenous variables; (2) it allows any number of instrumental variables in each alternative; and (3) it allows positive and/or negative correlations between any choice alternatives. For parameter estimation, we also propose a Bayesian Markov chain Monte Carlo algorithm that can be accommodated in more extended model structures. The simulation study demonstrates that the proposed model addresses endogeneity while allowing correlations between the choice alternatives. Meanwhile, the simulation also implies that the users need to pay attention to the setting of the prior distribution when an endogenous variable of interest is binary, even if the sample size is moderate. The proposed model will be a useful tool in disciplines in which both endogeneity and correlations between choice alternatives are major concerns.

Discrete mixture (DM) models recognize the presence of heterogeneity across individuals in a given population. In the context of a public land use discrete choice experiment, we use DM models to allow for respondent behavior to probabilistically mix over multiple competing process heuristics. We pairwise combine the Random Utility Model (RUM), Contextual Concavity Model (CCM), and Random Regret Minimization (RRM) heuristic into three DM models, in which the probability of an individual adhering to a particular heuristic is modeled as a function of sociodemographic characteristics. We present a comprehensive Bayesian analysis for which we explicitly describe prior selection, inferential procedures, and model comparison metrics. We use a fully Bayesian information criterion to rank the models. We find evidence that responses are best modeled using random regret. After accounting for preference heterogeneity, the DM models estimate two latent groups of decision makers. For the DM models, we develop a novel algorithm to calculate posterior-weighted willingness to pay estimates for improvements in different public park amenities in Polk County, Iowa.

Applications of discrete choice models in personalization are becoming increasingly popular among researchers and practitioners. However, in such systems, when users are presented with successive menus (or choice situations), the alternatives and attributes in each menu depend on the choices made by the user in the previous menus. This gives rise to endogeneity which can result in inconsistent estimates. Our companion paper, Danaf et al. (2020), showed that the estimates are only consistent when the entire choice history of each user is included in estimation. However, this might not be feasible because of computational constraints or data availability. In this paper, we present a control-function (CF) correction for the cases where the choice history cannot be included in estimation. Our method uses the attributes of non-personalized attributes as instruments, and applies the CF correction by including interactions between the explanatory variables and the first stage residuals. Estimation can be done either sequentially or simultaneously, however, the latter is more efficient (if the model reflects the true data generating process). This method is able to recover the population means of the distributed coefficients, especially with a long choice history. The variances are underestimated, because part of the inter-consumer variability is explained by the residuals, which are included in the systematic utility. However, the population variances can be computed from the estimation results. The modified utility equations (which include the residuals) can be used in forecasting and model application, and provide superior fit and predictions.

Case 1 best–worst scaling (BWS1) has been used in a wide variety of research fields. BWS1 is attractive, relative to discrete choice experiments, because individual’s preferences for items can be easily measured. Despite the relative ease of implementation, BWS1 analysis still requires the use of software packages. When used in conjunction with other packages, the new and revised functions in the package support.BWS allow BWS1 analysis to be conducted using either the counting approach or the modeling approach. Additionally, a new function that simulates responses to BWS1 questions allows discipline specific BWS1 examples to be created for teaching purposes. To make it easier for novice users to implement BWS1 analysis with R, the package RcmdrPlugin.BWS1, that integrates with R Commander has been developed. A free web tutorial for BWS1 in R has also been developed. This paper explains the features of the latest version of support.BWS, along with the new package RcmdrPlugin.BWS1, and illustrates how these packages work.