Journal of Choice Modelling最新文献

This paper builds upon the work of Professor Marley, who, since the beginning of his long research career, has proposed rigorous axiomatics in the area of probabilistic choice models. Our study concentrates on models that can be applied to best and worst choice scaling experiments. We focus on those among these models that are based on strong assumptions about the underlying ranking of the alternatives with which the individual is assumed to be endowed when making the choice. Taking advantage of an inclusion–exclusion identity that we showed a few years ago, we propose a variety of best–worst choice probability models that could be implemented in software packages that are flourishing in this field.

The Cube model (Mallahi-Karai and Diederich, 2019) is a dynamic-stochastic approach for decision making situations including multiple alternatives. The underlying model is a multivariate Wiener process with drift, and its dimension is related to the number of alternatives in the choice set. Here we modify the model to account for Best–Worst settings. The choices are made in a number of episodes allowing the alternatives to be ranked from best to worst or from worst to best. The model makes predictions with respect to choice probabilities and (mean) choice response times. We show how the model can be implemented using Markov chains and test the model and a simpler variation of it on data from Hawkins et al. (2014b).

This paper investigates the role of the outside good utility function on admissible substitution patterns in multiple discrete/continuous demand models. We first present a set of novel results that characterize the functional form of quantity price effects within this class of models. The results highlight the relative inflexibility of many standard outside good utility functions. We then propose a new outside good utility function that admits more flexible marginal utility curves. Our empirical analysis uses household scanner panel data from the potato chip category, where we find empirical support for non-standard rates of satiation for the outside good. We then show how the restrictive substitution patterns induced by standard utility specifications may distort price elasticities and the evaluation of loyalty coupon targeting programs.

Previous studies on modelling the microscopic behaviour of pedestrians have focused on conflict resolution among pedestrians in pedestrian-pedestrian interactions. Many of these models propose alternate mechanisms to avoid conflicts by introducing repulsive forces between pedestrians or a set of predefined rules stating the precedence of movements to sidestep obstacles and other pedestrians. However, the possibility of formulating the decision-making mechanism pedestrians use to overcome conflicts as a gap-seeking behaviour has not been explored. In this study, resolving conflicts between opposing pedestrians is modelled as gap choice decisions made by individuals. Pedestrians looking for gaps or spaces in a crowd to facilitate their movement form the basis for such an analysis. The study compares pedestrians' gap acceptance behaviour across two scenarios: pedestrian movement in a field setup (Kumbh Mela) and a controlled experiment. Multiple gap choice decisions of individuals are modelled to understand the effect of individual-level heterogeneity on gap choices. Apart from the gap duration, spacing, position of gap, linear density, age, and presence of luggage significantly influenced the gap choices. Model validation is done using appropriate methods for both field and experimental data. The bootstrap method of internal validation and holdout validation is used to assess the performance of the estimated model on field data and experimental data, respectively. It is seen that the models have reasonable predictive and discriminative abilities. The analysis results also indicate that pedestrians tend to force gaps to facilitate movement in their natural state. Consequently, controlled experiments might have limitations in reproducing or motivating the participants to behave like a crowd.

In discrete choice experiment (DCE) studies, selecting the appropriate sample size remains a challenge. The question of the required sample size for a DCE is addressed in the literature in two distinct approaches: a rule-of-thumb approach and an approach based on the statistical error of the parameter of interest. The former is less accurate and does not depend on the desired power and significance level, whereas the latter requires knowing the complete design which may not be known at the planning stage. This paper proposes a new rule of thumb as well as a new regression-based method that requires knowing certain design characteristics rather than the complete design and takes into account the power and significance level. We compare the sample size estimated using the proposed methods with the true required sample size based on the statistical error of the parameter of interest and the approximations given by the existing rules of thumb. The results show that both the new rule of thumb and the regression-based approach improve the magnitude and proportion of underestimation compared to the most commonly used rule of thumb of Orme. Though the proposed approaches perform in general similarly to Tang’s rule which improves Orme’s rule, they seem to do better for large settings in terms of the number of choice sets and the number of alternatives per choice set in reducing underestimation. Moreover, we have demonstrated the possibility to adapt the regression-based approaches to take into account other scenarios and choice set complexity.

We propose a modeling framework that uses only cross-sectional data to disentangle labor supply and demand choices simultaneously. This modeling framework extends the labor-market analytical toolkits to adapt to environments where data are limited, flexibility in working hours is lacking, or structural changes are present, as is the case in most emerging and low-income countries. We showcase our model by using the 2011 China Household Finance Survey to decipher labor market choices in urban China. We find that the main discrepancies in labor supply between males and females are driven by the number and age of children, the lower utility of working rather than fewer job opportunities for females, and larger impacts of education and work experience on females’ job opportunities. Household wealth in the form of ‘cash inflow’ incentivizes individuals not to work, while wealth in the form of ‘stock’ induces higher utility to work for both males and females. The interpretation of empirical findings hinges on particular assumptions that might be disputed.

In this article we propose two-step generalized method of moment (GMM) procedure for a Spatial Binary Probit Model. In particular, we propose a series of two-step estimators based on different choices of the weighting matrix for the moments conditions in the first step, and different estimators for the variance–covariance matrix of the estimated coefficients. In the context of a Monte Carlo experiment, we compare the properties of these estimators, a linearized version of the one-step GMM and the recursive importance sampler (RIS). Our findings reveal that there are benefits related both to the choice of the weight matrix for the moment conditions and in adopting a two-step procedure.

Subjective value has long been measured using binary choice experiments, yet responses like willingness-to-pay prices can be an effective and efficient way to assess individual differences risk preferences and value. Tony Marley’s work illustrated that dynamic, stochastic models permit meaningful inferences about cognition from process-level data on paradigms beyond binary choice, yet many of these models remain difficult to use because their likelihoods must be approximated from simulation. In this paper, we develop and test an approach that uses deep neural networks to estimate the parameters of otherwise-intractable behavioral models. Once trained, these networks allow for accurate and instantaneous parameter estimation. We compare different network architectures and show that they accurately recover true risk preferences related to utility, response caution, anchoring, and non-decision processes. To illustrate the usefulness of the approach, it was then applied to estimate model parameters for a large, demographically representative sample of U.S. participants who completed a 20-question pricing task — an estimation task that is not feasible with previous methods. The results illustrate the utility of machine-learning approaches for fitting cognitive and economic models, providing efficient methods for quantifying meaningful differences in risk preferences from sparse data.

Forecasting the future impact of climate change on migration is difficult, for many reasons, including the interactive and dynamic nature of many decisions and the heterogeneity of behavior. One popular solution, agent-based models (ABM) cope well with dynamics and heterogeneity, but often lack rigorous foundations in terms of individual behavior. Moreover, given limited exposure to actual climate change, it can be a challenge to build adequate behavioral models of migration choice based on historical data. To tackle this issue, we build an ABM of future migration using a bespoke choice experiment (CE) designed to examine intention to migrate among farmers living in the Vietnamese Mekong Delta (VMD). In the CE, respondents are asked to make migration choices for scenarios constructed using six attributes: drought intensity, flood frequency, income gain from migration, migration networks, neighbors' choice, and crop choice restriction. The simulation runs to 2050 and is based on two scenarios of future global emissions of greenhouse gases—Representative Concentration Pathway (RCP) 4.5 and RCP8.5. The results suggest potentially high levels of migration as a result of climate change and the particular importance of positive feedback from pre-existing migration and neighbor's choices. The results also suggest that crop-restriction regulations have a significant impact on migration for coastal provinces of VMD. Finally, we find that migration drivers vary significantly across provinces, which suggests the policymakers point to targeted action for each province. In summary, the study demonstrates how integrating CE into ABM can foster the predictive modeling of climate-induced migration.

Two-attribute-two-alternative stated choice experiments are widely used to infer the Value-of-Travel-Time (VTT) distribution. Two-attribute-two-alternative stated choice experiments have the advantage that their data can be analysed using nonparametric models, which allow for the inference of the VTT distribution without having to impose assumptions on its shape. However, a software package that enables researchers to estimate nonparametric models promptly is currently lacking. As a result, nonparametric models are underused. This paper aims to fill this software void. It presents NP4VTT, a Python package that enables researchers to estimate and compare nonparametric models in a fast and convenient way. It comprises five nonparametric models for estimating the VTT distribution from data coming from two-attribute-two-alternative stated choice experiments. We illustrate the use of NP4VTT by applying it to the Norwegian 2009 VTT data. We hope this software package will help researchers studying the VTT make more informed decisions concerning the shape of the VTT distribution and encourages the use and development of nonparametric models for choice behaviour analyses.