nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2023‒05‒15
sixteen papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. CHOICE – What Can Go Wrong? By Daniel McFadden
  2. Penalized Likelihood Inference with Survey Data By Joann Jasiak; Purevdorj Tuvaandorj
  3. Sharing values for multi-choice games: an axiomatic approach By David Lowing; Makoto Yokoo
  4. The strategic use of social identity By Tom Lane
  5. Recursive Preferences and Ambiguity Attitudes By Massimo Marinacci; Giulio Principi; Lorenzo Stanca
  6. American Micromobility Panel: Part 1 By Fitch-Polse, Dillon T; Mohiuddin, Hossain; Fukushige, Tatsuya; Darr, Justin; Agarwal, Swati
  7. Faster estimation of dynamic discrete choice models using index sufficiency By Jackson Bunting; Takuya Ura
  8. Econometric analysis of consumer choice in the car market By Gorshkova Marina; Mirzoyan Ashot
  9. A Note on Quasi-Maximum-Likelihood Estimation in Hidden Markov Models with Covariate-Dependent Transition Probabilities By Demian Pouzo; Zacharias Psaradakis; Martín Sola
  10. Slow Traffic, Fast Food: The Effects of Time Lost on Food Store Choice By Bencsik, Panka; Lusher, Lester; Taylor, Rebecca L.C.
  11. Happy Times: Measuring Happiness Using Response Times By Shuo Liu; Nick Netzer
  12. Identification of ex ante returns using elicited choice probabilities By Romauld Méango
  13. Traceability, value, and trust in the coffee market: A natural experiment in Ethiopia By Ludovic Mbakop; Glenn Jenkins; Leonard Leung; Kamil Sertoglu
  14. Intrinsic Preferences for Autonomy By Jana Freundt; Holger Herz; Leander Kopp
  15. Individual Welfare Analysis: Random Quasilinear Utility, Independence, and Confidence Bounds By Junlong Feng; Sokbae Lee
  16. The Value of Electricity Reliability: Evidence from Battery Adoption By Brown, David B.; Muehlenbachs, Lucija

  1. By: Daniel McFadden
    Abstract: The elegant economic picture of rational consumers achieving Pareto optimality through trade in decentralized self-organized markets is blurred by market imperfections and choices inconsistent with consumer self-interest. Behavioral economics has documented these errors in choice, and considered interventions that can mitigate harm to individuals from bad choices. This essay considers more broadly market distortions that arise when sellers design and market products to exploit consumer errors, and suggests market management policies to mitigate these distortions. I give examples in which consumers’ lack of attention and diligence in collecting, filtering, and processing information has an outsize effect on market outcomes. I discuss identification and estimation of a two-stage model of decision-making, with attention determined in the first stage, and choice among alternatives described in the second stage. The stages in this model are linked by unobservable factors and identified by available information specific to each. I use this model to quantify the effects of inattention in a market for health insurance.
    JEL: D01 D04 D15 D18 D47 D83 D91 L14 L15
    Date: 2023–04
  2. By: Joann Jasiak; Purevdorj Tuvaandorj
    Abstract: This paper extends three Lasso inferential methods, Debiased Lasso, $C(\alpha)$ and Selective Inference to a survey environment. We establish the asymptotic validity of the inference procedures in generalized linear models with survey weights and/or heteroskedasticity. Moreover, we generalize the methods to inference on nonlinear parameter functions e.g. the average marginal effect in survey logit models. We illustrate the effectiveness of the approach in simulated data and Canadian Internet Use Survey 2020 data.
    Date: 2023–04
  3. By: David Lowing (Kyushu University); Makoto Yokoo (Kyushu University)
    Abstract: A Sharing value for transferable utility games distributes the Harsanyi dividend of each coalition among the players in the coalition's support. Such distribution is done according to a certain sharing system that determines the Sharing value. In this paper, we extend Sharing values to multi-choice games. Multi-choice games are a generalization of transferable utility games in which players have several activity levels. Unlike in transferable utility games, there is no straightforward way to interpret the support of a coalition in a multi-choice game. This makes it more tedious to distribute the Harsanyi dividend of a multi-choice coalition. We consider three possible interpretations of the support of a multi-choice coalition. Based on these interpretations, we derive three families of Sharing values for multi-choice games. To conduct this study, we discuss novel and classical axioms for multi-choice games. This allows us to provide an axiomatic foundation for each of these families of values.
    Keywords: Multi-choice games, Sharing values, Harsanyi set
    Date: 2023–03–08
  4. By: Tom Lane (University of Nottingham)
    Abstract: The importance of social identities (e.g. race, gender, political ideology) in economic interactions is well established, but little is known about how people strategically manipulate the visibility or salience of their multiple identity types. This paper experimentally explores a common type of situation in which one party can choose between different identity characteristics to truthfully reveal about oneself before entering an economic exchange. Results demonstrate the choice this party makes has substantial potential to influence their payoff: individuals can increase earnings by around 22% by selecting the characteristic most favoured by their counterpart, relative to choosing randomly. Anticipating discriminatory treatment, individuals make strategic choices over which characteristic to reveal, and benefit from a broadly accurate understanding of which dimensions of social identity counterparts will more strongly discriminate along. However, they only reap a fraction of the potential returns from strategic social identity revelation, partly because beliefs about counterparts’ likely behaviour are saddled with misperceptions (for instance, overestimating likely in-group favouritism). Approximately half of individuals display willingness to sacrifice expected payoffs in exchange for making their preferred characteristics visible, suggesting that intrinsic utility is derived from social identity.
    Keywords: Social Identity; Multidimensionality; Discrimination; Prediction Accuracy; Strategic Revelation
    Date: 2023–01
  5. By: Massimo Marinacci; Giulio Principi; Lorenzo Stanca
    Abstract: We illustrate the strong implications of recursivity, a standard assumption in dynamic environments, on attitudes toward uncertainty. In intertemporal consumption choice problems, recursivity always implies constant absolute ambiguity aversion (CAAA) when applying the standard dynamic extension of monotonicity. Our analysis also yields a functional equation called "generalized rectangularity", as it generalizes the standard notion of rectangularity for recursive maxmin preferences to general certainty equivalents. Our results highlight that if uncertainty aversion is modeled as a form of convexity of preferences, recursivity limits us to only recursive variational preferences.
    Date: 2023–04
  6. By: Fitch-Polse, Dillon T; Mohiuddin, Hossain; Fukushige, Tatsuya; Darr, Justin; Agarwal, Swati
    Abstract: This report presents preliminary findings from the American Micromobility Panel, the largest study of shared micromobility services in the United States incorporating riders from multiple major operators. Micromobility services (bike-share and scooter-share) have recently emerged in many U.S. cities. Given that the substitution of bicycling, scooting, and other small vehicle travel for car travel will help cities reach numerous planning goals (e.g., accessibility, emissions, climate, health, equity, etc.), there is a need for understanding the effects of these mobility services. The purpose of this study was to examine the impact of micromobility services on travel behavior and outcomes such as mode shift, car ownership, access, equity, safety, and physical activity. The authors surveyed shared micromobility service users in 48 U.S. cities with two different surveys in Summer 2022: a 21-day smartphone-based travel diary (2206 participants with 183, 483 trips), and an online follow-up survey of travel diary participants (657 valid responses). Car substitution rates, including private car and ride-hailing, show strong variation by city size and micromobility vehicle type. Through self-report, micromobility seems to have had at least a partial influence on the decision to purchase a car, perhaps as a part of a long-term car use reduction effort/plan. Participants showed positive attitudes toward using public transit, but a small portion of trips to access or egress from transit facilities were made by the participants. Instead, the participants more generally showed a transit substitution effect when using micromobility services. Results also suggest that bike-share and scooter-share use may be influenced in opposing ways by participant income. Half of participants had at least once experienced that they could not find an available vehicle nearby, suggesting a sizeable supply constraint on demand for the services to satisfy existing micromobility user needs. The effect of micromobility services on increasing physical activity was slight given the physical activity it often replaced. Additionally, concerning safety, participants tended to agree that bike-share is safer than scooter-share, and participants tended to agree with the view that using micromobility improved their mental health. View the NCST Project Webpage
    Keywords: Social and Behavioral Sciences, Micromobility, shared mobility, travel survey, GPS data, bicycles, e-scooters, e-bikes
    Date: 2023–04–01
  7. By: Jackson Bunting; Takuya Ura
    Abstract: Many estimators of dynamic discrete choice models with permanent unobserved heterogeneity have desirable statistical properties but may be computationally intensive. In this paper we propose a method to quicken estimation for a broad class of dynamic discrete choice problems by exploiting index sufficiency. Index sufficiency implies a set of equality constraints which restrict the structural parameter of interest to belong in a subspace of the parameter space. We propose an estimator that uses the equality constraints, and show it is asymptotically equivalent to the unconstrained, computationally heavy estimator. Since the computational gains of our proposed estimator are due to the restriction of the parameter space to the subspace satisfying the equality constraints, we provide a series of results on the dimension of this subspace. Finally, we demonstrate the advantages of our approach by estimating a dynamic model of the U.K. fast food market.
    Date: 2023–04
  8. By: Gorshkova Marina (Department of Economics, Lomonosov Moscow State University); Mirzoyan Ashot (Department of Economics, Lomonosov Moscow State University)
    Abstract: The car market, like many others, needs a detailed study from the consumer's choice and preferences, because this aspect allows you to get to know the buyer better, understand what is important to him, and in which direction the industry as a whole is moving. The purpose of this work is to identify the determinants that determine the features of demand in the current economic situation in the personal transport market in Russia. The following analysis tools are used: clustering by the k means method, factor analysis by the principal components method, ordered logistic regression. Using the example of the Russian segment of the automotive market, 3 groups were identified and their preferences described, as well as the main factors influencing consumer choice among motorists and those who plan to buy personal transport were identified.
    Keywords: Car market, consumer behavior, consumer choice, clustering, principal component method, logistic regression
    JEL: L10 L62
    Date: 2022–11
  9. By: Demian Pouzo; Zacharias Psaradakis; Martín Sola
    Abstract: We consider hidden Markov models with a discrete-valued regime sequence whose transition probabilities are covariate-dependent. We show that consistent estimation of the parameters of the conditional distribution of the observable variables is possible via quasi-maximum-likelihood based on a (misspecified) mixture model without Markov dependence. Some related numerical results are also discussed.
    Keywords: Consistency; covariate-dependent transition probabilities; hidden Markov model; mixture model; quasi-maximum-likelihood; misspecified model.
    JEL: C12 C15 C22
    Date: 2023–02
  10. By: Bencsik, Panka (University of Chicago); Lusher, Lester (University of Hawaii at Manoa); Taylor, Rebecca L.C. (University of Sydney)
    Abstract: Time scarcity is one of the strongest correlates of fast food consumption. To estimate the causal effect of time lost on food choice, we match daily store-specific foot traffic data traced via smartphones to plausibly exogenous shocks in highway traffic data in Los Angeles. We find that on days when highways are more congested, individuals are more likely to dine out and less likely to grocery shop. The effects are particularly pronounced for afternoon rush hour traffic. Our results imply a net reduction in healthy food store choice due to time lost.
    Keywords: traffic congestion, time constraints, store choice, nutrition, fast food
    JEL: I12 I30 J22 R41
    Date: 2023–03
  11. By: Shuo Liu; Nick Netzer
    Abstract: Surveys that measure subjective states like happiness or preferences often generate discrete ordinal data. Ordered response models, which are commonly used to analyze such data, suffer from a fundamental identification problem. Their conclusions depend on unjustified assumptions about the distribution of a latent variable. In this paper, we propose using survey response times to solve that problem. Response times contain information about the distribution of the latent variable even among subjects who give the same survey response, through a chronometric effect. Using an online survey, we test and verify the existence of the chronometric effect. We then provide theoretical conditions under which group differences in happiness or other variables are detectable based on response time data without making distributional assumptions. In our survey, we find evidence supporting the assumptions of traditional ordered response models for some common survey questions but not for others.
    Keywords: surveys, ordinal data, response times, non-parametric, identification
    JEL: C14 D60 D91 I31
    Date: 2023
  12. By: Romauld Méango
    Abstract: This paper studies the identification of perceived ex ante returns in the context of binary human capital investment decisions. The environment is characterised by uncertainty about future outcomes, with some uncertainty being resolved over time. In this context, each individual holds a probability distribution over different levels of returns. The paper uses the hypothetical choice methodology to identify nonparametrically the population distribution of several individual-specific distribution parameters, which are crucial for counterfactual policy analyses. The empirical application estimates perceived returns on overstaying for Afghan asylum seekers in Germany and evaluates the effect of assisted voluntary return policies.
    Date: 2023–03–31
  13. By: Ludovic Mbakop (Department of Economics, Eastern Mediterranean University, Famagusta, Northern Cyprus via Mersin 10, Turkey); Glenn Jenkins (Queen's University); Leonard Leung (Asian Development Bank, Manilla, The Philippines); Kamil Sertoglu (Department of Economics, Eastern Mediterranean University, Famagusta, Northern Cyprus via Mersin 10, Turkey)
    Abstract: This study measures the impact of traceability attributes on international buyers’ willingness to pay for coffee produced in Ethiopia and the impact of accurate information on the production location of the coffee on the pricing according to its type and grade. Two sets of regressions models were used to investigate the important determinant factors affecting the export prices of trader and producer coffee, one each for trader and producer coffee, to measure the impact of the ECX on the prices and to evaluate the effect of the coffee types and grades on the prices. The results show that after coffee was forced to be traded via the ECX, traceable coffee export prices increased more than the reported price of non-traceable coffee. We also found that after the introduction of the ECX, the reported export prices of coffee were much more closely aligned to the movements in the international prices of coffee than before the ECX. Furthermore, we also find evidence that exporters and overseas buyers do not trust the results of the inspection and grading of coffee by the ECX unless traceability is also present. This is the first study to evaluate foreign buyers’ willingness to pay for the attribute of traceability of Ethiopian coffee and to see how traceability has affected buyers’ trust in the grades given by the ECX for the coffee it graded.
    Keywords: Ethiopian commodity exchange, Ethiopian coffee, Coffee traceability, Commoditization
    JEL: D40 E23 Q17
    Date: 2023–04
  14. By: Jana Freundt; Holger Herz; Leander Kopp
    Abstract: Personal autonomy has been argued to be fundamental to well-being and is often discussed as an important driver of economic and political behavior. Yet, preferences for autonomy are not well understood, because their identification requires the separation of instrumental value attached to autonomous choice. We propose a novel elicitation method that solves this identification challenge. We establish the existence of intrinsic preferences for choice autonomy and show substantial heterogeneity in a large online sample. We further study their antecedents by relating them to existing personality scales and socioeconomic characteristics. Finally, we test their association with other preferences, attitudes and beliefs.
    Keywords: autonomy, preference measurement, experiment
    JEL: D01 D90 C91
    Date: 2023
  15. By: Junlong Feng; Sokbae Lee
    Abstract: We introduce a novel framework for individual-level welfare analysis. It builds on a parametric model for continuous demand with a quasilinear utility function, allowing for unobserved individual-product-level preference shocks. We obtain bounds on the individual-level consumer welfare loss at any confidence level due to a hypothetical price increase, solving a scalable optimization problem constrained by a new confidence set under an independence restriction. This confidence set is computationally simple, robust to weak instruments and nonlinearity, and may have applications beyond welfare analysis. Monte Carlo simulations and two empirical applications on gasoline and food demand demonstrate the effectiveness of our method.
    Date: 2023–04
  16. By: Brown, David B.; Muehlenbachs, Lucija (Resources for the Future)
    Abstract: To avoid electric-infrastructure-induced wildfires, millions of Californians have had their power cut for hours to days at a time. We show that rooftop solar-plus-battery-storage systems increased in zip codes with the longest power outages. Rooftop solar panels alone will not help a household avert outages, but a solar-plus-battery-storage system will. Using this fact, we obtain a revealed-preference estimate of the willingness to pay for electricity reliability, the Value of Lost Load, a key parameter for electricity market design. Our estimate, of around $4, 300/MWh, suggests California's wildfires-prevention outages resulted in losses from foregone consumption of $322 million to residential electricity consumers.
    Date: 2023–04–18

This nep-dcm issue is ©2023 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.