nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2022‒07‒25
nine papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. Regulating Matching Markets with Constraints: Data-driven Taxation By Akira Matsushita; Kei Ikegami; Kyohei Okumura; Yoji Tomita; Atsushi Iwasaki
  2. Identifying nontransitive preferences By Carlos Alós-Ferrer; Ernst Fehr; Michele Garagnani
  3. Strictly log-concave probability distributions in discrete response models By Eleni Aristodemou
  4. Sharing the Cost of a Gas Distribution Network By David Lowing
  5. El contraste reset en los modelos logit y probit. Un estudio de Monte Carlo By José Antonio Pérez Mínguez; Inmaculada Villanúa Martín
  6. Estimating willingness to pay for public health insurance while accounting for protest responses: A further step towards universal health coverage in Tunisia? By Mohammad Abu‐zaineh; Olivier Chanel; Khaled Makhloufi
  7. Comparison of Bayesian and Sample Theory Parametric and Semiparametric Binary Response Models By Xiangjin Shen; Iskander Karibzhanov; Hiroki Tsurumi; Shiliang Li
  8. Skewness preferences: Evidence from online poker By Dertwinkel-Kalt, Markus; Kasinger, Johannes; Schneider, Dmitrij
  9. Willingness to use MaaS in a developing country By Rodrigo Gandia; Fabio Antonialli; Julia Oliveira; Joel Sugano; Isabelle Nicolaï; Izabela Cardoso Oliveira

  1. By: Akira Matsushita; Kei Ikegami; Kyohei Okumura; Yoji Tomita; Atsushi Iwasaki
    Abstract: This paper develops a framework to conduct a counterfactual analysis to regulate matching markets with regional constraints that impose lower and upper bounds on the number of matches in each region. Our work is motivated by the Japan Residency Matching Program, in which the policymaker wants to guarantee the least number of doctors working in rural regions to achieve the minimum standard of service. Among the multiple possible policies that satisfy such constraints, a policymaker wants to choose the best. To this end, we develop a discrete choice model approach that estimates the utility functions of agents from observed data and predicts agents' behavior under different counterfactual policies. Our framework also allows the policymaker to design the welfare-maximizing tax scheme, which outperforms the policy currently used in practice. Furthermore, a numerical experiment illustrates how our method works.
    Date: 2022–05
  2. By: Carlos Alós-Ferrer; Ernst Fehr; Michele Garagnani
    Abstract: Transitivity is perhaps the most fundamental choice axiom and, therefore, almost all economic models assume that preferences are transitive. The empirical literature has regularly documented violations of transitivity, but these violations pose little problem as long as they are simply a result of somewhat-noisy decision making and not a reflection of the deterministic part of individuals’ preferences. However, what if transitivity violations reflect individuals’ nontransitive preferences? And how can we separate nontransitive preferences from noise-generated transitivity violations–a problem that so far appears unresolved? Here we tackle these fundamental questions on the basis of a newly developed, non-parametric method which uses response times and choice frequencies to distinguish revealed preferences from noise. We extend the method to allow for nontransitive choices, enabling us to identify the share of weak stochastic transitivity violations that is due to nontransitive preferences. By applying the method to two different datasets, we document that a sizeable proportion of transitivity violations reflect nontransitive preferences. These violations cannot be accounted for by any noise or utility specification within the universe of random utility models. Finally, in spite of revealed transitivity violations, preferences estimated through our method predict choices out of sample better than standard parametric random-utility estimations.
    Keywords: Transitivity, stochastic choice, preference revelation, predicting choices
    JEL: D01 D81 D91
    Date: 2022–07
  3. By: Eleni Aristodemou
    Abstract: This paper extends the results of Prekopa (1973, 1980) on strictly log-concave cumulative distributions to strictly log-concave probability distributions. It is shown that if a random variable follows a strictly logarithmic concave distribution, then the probability that the random variable is contained within a convex polytope is also strictly logarithmic concave. This formal result can be useful for identification and estimation of a general class of linear-index discrete response models, where the additively separable unobservable follows a strictly log-concave distribution.
    Keywords: Discrete Response Models; Strict Log-Concavity
    Date: 2022–07–06
  4. By: David Lowing (GATE Lyon Saint-Étienne - Groupe d'analyse et de théorie économique - ENS Lyon - École normale supérieure - Lyon - UL2 - Université Lumière - Lyon 2 - UCBL - Université Claude Bernard Lyon 1 - Université de Lyon - UJM - Université Jean Monnet [Saint-Étienne] - Université de Lyon - CNRS - Centre National de la Recherche Scientifique)
    Abstract: A gas distribution network connects consumers to a source in gas. It is managed by a network operator, whose task incurs various costs, some of which may not be attributable to a particular consumer. Assuming that the operator wishes to recover these costs by charging for its services, the problem is then to determine how much each consumer should pay. In other words, how should these costs be shared among consumers. In this paper, we address this problem and propose cost sharing rules that depend on the network and the demands of the consumers. To that end, we adopt a normative approach and resort to three principles: (i) the independence of higher demands principle, (ii) the connection principle and (iii) the uniformity principle. Applying (i) and (ii), we derive the Connection rule and applying (i) and (iii), we derive the Uniform rule. It appears that (ii) and (iii) are incompatible. In order to make a trade-off between these two principles, we propose the Mixed rules, which compromise between the Connection rule and the Uniform rule. For each cost sharing rule, an axiomatic characterization is provided. Then, we show that the Connection rule coincides with the multi-choice Shapley value of a specific multi-choice game derived from the network and the demands of the consumers. Moreover, the Connection rule is in the Core of this specific multi-choice game. Similarly, we show that the Uniform rule coincides with the multi-choice Equal division value and the Mixed rules coincide with the multi-choice Egalitarian Shapley values.
    Keywords: Gas distribution network,Cost sharing rules,Axiomatization,Multi-choice games
    Date: 2022–05–27
  5. By: José Antonio Pérez Mínguez (Universidad de Zaragoza); Inmaculada Villanúa Martín (Universidad de Zaragoza)
    Abstract: En este trabajo se analiza el comportamiento del contraste Reset en los modelos binarios probit y logit. Este es un contraste general de especificación ampliamente utilizado en modelos lineales clásicos, que permite captar algunos errores cometidos en nuestras modelizaciones. A través de simulaciones se estudia su funcionamiento en estimaciones probit y logit, tanto si la especificación es correcta como si existen errores por variables omitidas, heterocedasticidad o incorrecta función de distribución de la perturbación. Los resultados muestran un buen comportamiento del contraste cuando el modelo está correctamente especificado, y nos permiten conocer la sensibilidad del contraste ante determinados errores.
    Keywords: variables omitidas, heterocedasticidad, error de especificación, tamaño, potencia.
    JEL: C12 C15 C25 C52
    Date: 2022–02
  6. By: Mohammad Abu‐zaineh (AMSE - Aix-Marseille Sciences Economiques - EHESS - École des hautes études en sciences sociales - ECM - École Centrale de Marseille - CNRS - Centre National de la Recherche Scientifique - AMU - Aix Marseille Université, SMPM - Faculty of Medical and Paramedical Sciences, School of Public Administration and Development Economics, Doha Institute for Graduate Studies); Olivier Chanel (AMSE - Aix-Marseille Sciences Economiques - EHESS - École des hautes études en sciences sociales - ECM - École Centrale de Marseille - CNRS - Centre National de la Recherche Scientifique - AMU - Aix Marseille Université); Khaled Makhloufi (SESSTIM - U1252 INSERM - Aix Marseille Univ - UMR 259 IRD - Sciences Economiques et Sociales de la Santé & Traitement de l'Information Médicale - IRD - Institut de Recherche pour le Développement - AMU - Aix Marseille Université - INSERM - Institut National de la Santé et de la Recherche Médicale)
    Abstract: Introduction: Developing countries face major challenges in implementing universal health coverage (UHC): a widespread informal sector, general discontent with rising economic insecurity and inequality and the rollback of state and public welfare. Under such conditions, estimating the demand for a health insurance scheme (HIS) on voluntary basis can be of interest to accelerate the progress of UHC-oriented reforms. However, a major challenge that needs to be addressed in such context is related to protest attitudes that may reflect, inter alia, a null valuation of the expected utility or unexpressed demand. Methods: We propose to tackle this by applying a contingent valuation survey to a non-healthcare-covered Tunisian sample vis-à-vis joining and paying for a formal HIS. Our design pays particular attention to identifying the nature of the willingness-to-pay (WTP) values obtained, distinguishing genuine null values from protest values. To correct for potential selection issues arising from protest answers, we estimate an ordered-Probit-selection model and compare it with the standard Tobit and Heckman sample selection models. Results: Our results support the presence of self-selection and, by predicting protesters' WTP, allow the "true" sample mean WTP to be computed. This appears to be about 14% higher than the elicited mean WTP. Conclusion: The WTP of the poorest non-covered respondents represents about one and a half times the current contributions of the poorest formal sector enrolees, suggesting that voluntary participation in the formal HIS is feasible.
    Date: 2022–05–23
  7. By: Xiangjin Shen; Iskander Karibzhanov; Hiroki Tsurumi; Shiliang Li
    Abstract: This study proposes a Bayesian semiparametric binary response model using Markov chain Monte Carlo algorithms since this Bayesian algorithm works when the maximum likelihood estimation fails. Implementing graphic processing unit computing improves the computation time because of its efficiency in estimating the optimal bandwidth of the kernel density. The study employs simulated data and Monte Carlo experiments to compare the performances of the parametric and semiparametric models. We use mean squared errors, receiver operating characteristic curves and marginal effects as model assessment criteria. Finally, we present an application to evaluate the consumer bankrupt rates based on Canadian TransUnion data.
    Keywords: Credit risk management; Econometric and statistical methods transmission
    JEL: C1 C14 C35 C51 C63 D1
    Date: 2022–07
  8. By: Dertwinkel-Kalt, Markus; Kasinger, Johannes; Schneider, Dmitrij
    Abstract: We investigate what statistical properties drive risk-taking in a large set of observational panel data on online poker games (n=4,450,585). Each observation refers to a choice between a safe "insurance" option and a binary lottery of winning or losing the game. Our setting offers a real-world choice situation with substantial incentives where probability distributions are simple, transparent, and known to the individuals. We find that individuals reveal a strong and robust preference for skewness. The effect of skewness is most pronounced among experienced and losing players but remains highly significant for winning players, in contrast to the variance effect.
    Keywords: Online Poker,Risk Attitudes,Risk Preferences,Choice under Risk
    JEL: D01 D81 G40
    Date: 2022
  9. By: Rodrigo Gandia; Fabio Antonialli; Julia Oliveira; Joel Sugano; Isabelle Nicolaï (LGI - Laboratoire Génie Industriel - CentraleSupélec - Université Paris-Saclay); Izabela Cardoso Oliveira
    Abstract: Mobility as a Service (MaaS) presents a shift from existing ownership-based transports and towards access-based ones and it has been recently gaining ground in urban mobility. MaaS is still surrounded by uncertainties and, its development and applicability are mainly centered in developed countries. However, MaaS is modular, adaptable and applicable to several realities. In this sense, this study aims to examine the perception of different transport models among students and to find the profile that can predict respondents' willingness to use MaaS in a developing country. This survey was applied to over 300 university students in a Brazilian city (Lavras). Using the CART algorithm, it was obtained classification trees to predict favorable responses related to MaaS use, based on several predictor variables (socio-economic characteristics, means of transport used, distance and other). It was observed that, car users are a little less sensitive to cost than non-car users. For car users, commute alternatives that take longer, with less flexibility and availabilityeven when offered at lower costsare not appealing, while non-car users accept and spend more time whether lower costs are available. Also, in general, the tree-based classification model predicted a positive adherence possibility for a MaaS scheme for both car users and non-car users (69%). As conclusions, this study suggests a willingness to MaaS model for creating value for commuters in a developing country. It was found that many MaaS' characteristics (e.g. app payment, transport integration, monthly plan, customization, son on.) presented a positive predicted possibility of substitution, especially for millennials. Also, it was found that bicycle may be a modal that can be explored for MaaS schemes worldwide, and casual carpooling could be used as strategy to apply MaaS in places where the public transport lacks efficiency.
    Keywords: Mobility as a Service,Consumer behavior,Travel behavior,Urban mobility,Treebased classification model
    Date: 2021–01

This nep-dcm issue is ©2022 by Edoardo Marcucci. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.