nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2022‒01‒10
nine papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. Incorporating Search and Sales Information in Demand Estimation By Ali Hortaçsu; Olivia R. Natan; Hayden Parsley; Timothy Schwieg; Kevin R. Williams
  2. Yogurts Choose Consumers? Estimation of Random-Utility Models via Two-Sided Matching By Odran Bonnet; Alfred Galichon; Yu-Wei Hsieh; Keith O'Hara; Matt Shum
  3. Efficient counterfactual estimation in semiparametric discrete choice models: a note on Chiong, Hsieh, and Shum (2017) By Grigory Franguridi
  4. What's in it for me? Self-interest and preferences for distribution of costs and benefits of energy efficiency policies By Fanghella, Valeria; Faure, Corinne; Guetlein, Marie-Charlotte; Schleich, Joachim
  5. Optimal Price Targeting By Adam N. Smith; Stephan Seiler; Ishant Aggarwal
  6. Herd behavior in the choice of motorcycles: Evidence from Nepal By Nilkanth Kumar; Nirmal Kumar Raut; Suchita Srinivasan
  7. Computing Revealed Preference Goodness of fit Measures with Integer Programming By Thomas Demuynck; John Rehbeck
  8. Choice Determinants of a Smart Contract vs. Ambiguous Expert-Based Insurance: An Experiment By Giuseppe Attanasi; Marta Ballatore; Michela Chessa; Agnès Festré; Chris Ouangraoua
  9. Distance to Schools and Equal Access in School Choice Systems By Mariana Laverde

  1. By: Ali Hortaçsu; Olivia R. Natan; Hayden Parsley; Timothy Schwieg; Kevin R. Williams
    Abstract: We propose an approach to modeling and estimating discrete choice demand that allows for a large number of zero sale observations, rich unobserved heterogeneity, and endogenous prices. We do so by modeling small market sizes through Poisson arrivals. Each of these arriving consumers then solves a standard discrete choice problem. We present a Bayesian IV estimation approach that addresses sampling error in product shares and scales well to rich data environments. The data requirements are traditional market-level data and measures of consumer search intensity. After presenting simulation studies, we consider an empirical application of air travel demand where product-level sales are sparse. We find considerable variation in demand over time. Periods of peak demand feature both larger market sizes and consumers with higher willingness to pay. This amplifies cyclicality. However, observed frequent price and capacity adjustments offset some of this compounding effect.
    JEL: C10 C11 C13 C18 L93
    Date: 2021–12
  2. By: Odran Bonnet; Alfred Galichon; Yu-Wei Hsieh; Keith O'Hara; Matt Shum
    Abstract: The problem of demand inversion - a crucial step in the estimation of random utility discrete-choice models - is equivalent to the determination of stable outcomes in two-sided matching models. This equivalence applies to random utility models that are not necessarily additive, smooth, nor even invertible. Based on this equivalence, algorithms for the determination of stable matchings provide effective computational methods for estimating these models. For non-invertible models, the identified set of utility vectors is a lattice, and the matching algorithms recover sharp upper and lower bounds on the utilities. Our matching approach facilitates estimation of models that were previously difficult to estimate, such as the pure characteristics model. An empirical application to voting data from the 1999 European Parliament elections illustrates the good performance of our matching-based demand inversion algorithms in practice.
    Date: 2021–11
  3. By: Grigory Franguridi
    Abstract: I suggest an enhancement of the procedure of Chiong, Hsieh, and Shum (2017) for calculating bounds on counterfactual demand in semiparametric discrete choice models. Their algorithm relies on a system of inequalities indexed by cycles of a large number $M$ of observed markets and hence seems to require computationally infeasible enumeration of all such cycles. I show that such enumeration is unnecessary because solving the "fully efficient" inequality system exploiting cycles of all possible lengths $K=1,\dots,M$ can be reduced to finding the length of the shortest path between every pair of vertices in a complete bidirected weighted graph on $M$ vertices. The latter problem can be solved using the Floyd--Warshall algorithm with computational complexity $O\left(M^3\right)$, which takes only seconds to run even for thousands of markets. Monte Carlo simulations illustrate the efficiency gain from using cycles of all lengths, which turns out to be positive, but small.
    Date: 2021–12
  4. By: Fanghella, Valeria; Faure, Corinne; Guetlein, Marie-Charlotte; Schleich, Joachim
    Abstract: Public acceptability appears an essential condition for the success of lowcarbon transition policies. In this paper, we investigate the role of self-interest on citizens' preferences for the distribution of costs and of environmental benefits of energy efficiency policies. Using a discrete choice experiment on nationally representative household samples of Italy, Sweden, and the United Kingdom, we first investigate preferences for specific burden-sharing rules and for the distribution of policy environmental benefits accruing primarily in rural and/or urban areas. We examine the role of self-interest in a correlation manner by looking at the effects of income and of location of residency on preferences for these policy attributes. Moreover, we investigate the effect of self-interest on preferences for burden-sharing rules in a causal manner by exogenously priming subsets of participants to feel either rich or poor. Our results suggest that the polluter-pays rule is the most popular burden-sharing rule and an equalamount rule the least popular and that policies with environmental benefits accruing primarily in rural areas are less preferred, with some heterogeneity in preferences across the three countries. We also find evidence for self-interest, both through correlational and through causal approaches.
    Keywords: policy acceptability,self-interest,distributional fairness,discretechoice experiment,energy efficiency
    Date: 2021
  5. By: Adam N. Smith; Stephan Seiler; Ishant Aggarwal
    Abstract: We examine the profitability of personalized pricing policies that are derived using different specifications of demand in a typical retail setting with consumer-level panel data. We generate pricing policies from a variety of models, including Bayesian hierarchical choice models, regularized regressions, and classification trees using different sets of data inputs. To compare pricing policies, we employ an inverse probability weighted estimator of profits that explicitly takes into account non-random price variation and the panel nature of the data. We find that the performance of machine learning models is highly varied, ranging from a 21% loss to a 17% gain relative to a blanket couponing strategy, and a standard Bayesian hierarchical logit model achieves a 17.5% gain. Across all models purchase histories lead to large improvements in profits, but demographic information only has a small impact. We show that out-of-sample hit probabilities, a standard measure of model performance, are uncorrelated with our profit estimator and provide poor guidance towards model selection.
    Keywords: targeting, personalization, heterogeneity, choice models, machine learning
    JEL: C11 C33 C45 C52 D12 L11 L81
    Date: 2021
  6. By: Nilkanth Kumar (Center of Economic Research (CER-ETH), ETH Zurich, Zurich, Switzerland); Nirmal Kumar Raut (Central Department of Economics (CEDECON), Tribhuvan University, Kathmandu, Nepal); Suchita Srinivasan (Center of Economic Research (CER-ETH), ETH Zurich, Zurich, Switzerland)
    Abstract: This article sheds light on a scarcely explored area of research related to herd behavior in urban settings of developing economies, where the use of motorized twowheelers has been increasing rapidly. Using primary survey-based data from Nepal, we examine whether potential motorcycle buyers in the Kathmandu valley exhibit herd behavior or price-conscious behavior when making a hypothetical choice decision and then evaluate the determinants of the observed behavior. Using factor analysis, the paper identifies distinct homogeneous groups of respondents based on their preferences towards motorcycle attributes and on their psychological traits and attitudes. Not only do we find a prevalence of herding in the choice of motorcycles, the results also find strong suggestive evidence that, in addition to gender and income, several latent factors related to preferences and psychological traits might play a crucial role in determining the herd behavior. We discuss policy implications in the context of consumer behavior and environmental policy in the backdrop of rapid vehicle demand and dangerous air pollution levels.
    Keywords: herd behavior; determinants; motorcycle choice; psychological factors; bounded rationality; Nepal
    JEL: D12 D83 D91 Q58
    Date: 2022–01
  7. By: Thomas Demuynck; John Rehbeck
    Abstract: This paper develops mixed-integer linear programming (MILP) formulations to compute various revealed preference goodness-of-fit measures. We provide MILP formulations to compute the Houtman-Maks Index, the Average Varian Index, and the Minimum Cost Index when there are linear budgets. Next, we provide MILPs to compute minimal measurement error in expenditures, prices, and quantities. Finally, we extend our results to non-linear budgets. As a proof of concept, we compute various goodness-of-fit measures for experimental choice data sets from the literature. The maximal computation time is less than 3 seconds for all measures examined on these datasets.
    Keywords: Revealed preference; choice consistency; computation
    Date: 2021–11
  8. By: Giuseppe Attanasi (Université Côte d'Azur, France; GREDEG CNRS); Marta Ballatore (GREDEG CNRS; Université Côte d'Azur, France); Michela Chessa (Université Côte d'Azur, France; GREDEG CNRS); Agnès Festré (GREDEG CNRS; Université Côte d'Azur, France; The Arctic University of Norway, Tromsø, Norway); Chris Ouangraoua (GREDEG CNRS; Université Côte d'Azur, France)
    Abstract: This study proposes an analysis of behavioral factors (attitudes toward risk, ambiguity and reduction of compound lotteries) as choice determinants of a blockchain-based car insurance smart contract (henceforth, BCT-based SC) vs. an ambiguous expert-based one. In a laboratory experiment, we develop a toy model representing such a choice and complement it with a questionnaire in order to collect data concerning participants’ demographics, personality traits, and car use experience. Our results can inform policies aimed at improving the understanding of BCT-based SC in the case of car insurance services. In particular, they advocate for designing ad hoc policies depending on user’s experience with cars.
    Keywords: Laboratory experiments, Blockchain, Smart contracts, Technology adoption, Risk, Ambiguity, Compound lottery
    JEL: C81 C83 C91 D81 D91
    Date: 2021–12
  9. By: Mariana Laverde (Yale University)
    Abstract: This paper studies the limits of school choice policies in the presence of residential segregation. Using data from the Boston Public Schools choice system, I show that white prekindergarteners are assigned to higher-achieving schools than minority students, and that cross-race school achievement gaps under choice are no lower than would be generated by a neighborhood assignment rule. To understand why choicebased assignments do not reduce gaps in school achievement, I use data on applicants’ rank-order choices to estimate preferences over schools, and consider a series of counterfactual assignments. I find that half of the gap in school achievement between white and Black or Hispanic students is explained by minorities’ longer travel distance to high-performing schools. Differences in demand parameters explain a smaller fraction of the gap, while algorithm rules have no effect.
    Keywords: Boston Public Schools, residential segregation, school achievement, achievement gaps
    JEL: I21 J15 J61
    Date: 2022–01

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.