nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2023‒07‒10
nine papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. Rank-heterogeneous Preference Models for School Choice By Amel Awadelkarim; Arjun Seshadri; Itai Ashlagi; Irene Lo; Johan Ugander
  2. A Choice Experiment of Wyoming Residents’ Preferences Toward Water Resilience Improvement Programs By Van Sandt, Anders T.; Hansen, Kristiana M.; Ehmke, Mariah D.; Shinker, JJ; Paige, Ginger; Keller, Mary; Cooper, Kaatie; Landreville, Kristen Dawn
  3. Revealed preferences for dynamically inconsistent models By Federico Echenique; Gerelt Tserenjigmid
  4. The Dynamic Role of Subsidies in Promoting Global Electric Vehicle Sales By Tamara Sheldon; Rubal Dua
  5. Robust Data Regulation By Jose Higueras
  6. Free-Ridership in Subsidies for Company- and Private Electric Vehicles By Burra, Lavan T., Sommer, Stephan; Vance, Colin
  7. The Emergence of Economic Rationality of GPT By Yiting Chen; Tracy Xiao Liu; You Shan; Songfa Zhong
  8. The hedonic value of coastal amenities in peer-to-peer markets "Abstract: Coastal amenities are public goods that represent an important attraction for tourism activities. This paper studies consumers’ willingness to pay for beach characteristics using hedonic pricing methods. We examine the implicit economic value of several beach characteristics like sand type, width, longitude, accessibility, or frontage in the Airbnb rental market. Using data for 16, 663 Airbnb listings located in 67 municipalities of the Balearic Islands (Spain) during the summer of 2016, together with detailed information about the attributes of 263 beaches, our modelling approach considers interaction terms between the beach amenities and distance to the closest beach within a hedonic framework. Controlling for a set of listings’ characteristics, host features and municipality fixed effects, we find that Airbnb guests attach economic value to beach length, the presence of vegetation, the type of coastal frontage and beach accessibility and exclusivity. However, there is no evidence of price premiums depending on the beach width or the type of sand." By David Boto-García; Veronica Leoni
  9. Individual Causal Inference Using Panel Data With Multiple Outcomes By Wei Tian

  1. By: Amel Awadelkarim; Arjun Seshadri; Itai Ashlagi; Irene Lo; Johan Ugander
    Abstract: School choice mechanism designers use discrete choice models to understand and predict families' preferences. The most widely-used choice model, the multinomial logit (MNL), is linear in school and/or household attributes. While the model is simple and interpretable, it assumes the ranked preference lists arise from a choice process that is uniform throughout the ranking, from top to bottom. In this work, we introduce two strategies for rank-heterogeneous choice modeling tailored for school choice. First, we adapt a context-dependent random utility model (CDM), considering down-rank choices as occurring in the context of earlier up-rank choices. Second, we consider stratifying the choice modeling by rank, regularizing rank-adjacent models towards one another when appropriate. Using data on household preferences from the San Francisco Unified School District (SFUSD) across multiple years, we show that the contextual models considerably improve our out-of-sample evaluation metrics across all rank positions over the non-contextual models in the literature. Meanwhile, stratifying the model by rank can yield more accurate first-choice predictions while down-rank predictions are relatively unimproved. These models provide performance upgrades that school choice researchers can adopt to improve predictions and counterfactual analyses.
    Date: 2023–06
  2. By: Van Sandt, Anders T.; Hansen, Kristiana M.; Ehmke, Mariah D.; Shinker, JJ; Paige, Ginger; Keller, Mary; Cooper, Kaatie; Landreville, Kristen Dawn
    Keywords: Community/Rural/Urban Development, Environmental Economics and Policy, Research Methods/Statistical Methods
    Date: 2023
  3. By: Federico Echenique; Gerelt Tserenjigmid
    Abstract: We study the testable implications of models of dynamically inconsistent choices when planned choices are unobservable, and thus only "on path" data is available. First, we discuss the approach in Blow, Browning and Crawford (2021), who characterize first-order rationalizability of the model of quasi-hyperbolic discounting. We show that the first-order approach does not guarantee rationalizability by means of the quasi-hyperbolic model. This motivates consideration of an abstract model of intertemporal choice, under which we provide a characterization of different behavioral models -- including the naive and sophisticated paradigms of dynamically inconsistent choice.
    Date: 2023–05
  4. By: Tamara Sheldon; Rubal Dua (King Abdullah Petroleum Studies and Research Center)
    Abstract: We offer the most comprehensive analysis to date of global plug-in electric vehicle (PEV) subsidies. We accomplish this by estimating vehicle choice models for 23 countries using 2010–2019 sales data and using counterfactual simulations to assess the cost-effectiveness of PEV incentives.
    Keywords: Alternative fuels, Carbon market, Clean technology, Climate change
    Date: 2023–06–06
  5. By: Jose Higueras
    Abstract: I study how to regulate firms' access to consumer data when it is used for price discrimination and the regulator possesses non-Bayesian uncertainty about the correlation structure between data and willingness to pay. Therefore, it is unclear how the monopolist will segment the market. I characterize all policies that maximize worst-case consumer surplus: the regulator allows the monopolist to access data, if the database does not reveal a minority group of consumers.
    Date: 2023–05
  6. By: Burra, Lavan T., Sommer, Stephan; Vance, Colin
    Abstract: Consumer subsidies are commonly employed to incentivize the purchase of battery electric vehicles (BEVs), but free-ridership potentially undermines their effectiveness. The present study investigates BEV subsidies in Germany, distinguishing their effect between company- and private cars. Drawing on a panel of high-resolution car registration data, we use the estimates from a Poisson pseudo-maximum likelihood model to predict BEV registrations in the absence of the subsidy. We calculate aggregate free-rider rates of 19% for private cars and 43% for company cars. We further find that the cost of the subsidy per induced BEV among private consumers is €5, 400, while it is €7, 215 among companies. Overall, the estimates suggest that the subsidy is considerably less cost effective among company cars, which comprise 55% of new BEV sales.
    Keywords: Electric vehicles, consumer subsidy, company cars, free ridership
    JEL: H23 L91 Q58
    Date: 2023
  7. By: Yiting Chen; Tracy Xiao Liu; You Shan; Songfa Zhong
    Abstract: As large language models (LLMs) like GPT become increasingly prevalent, it is essential that we assess their capabilities beyond language processing. This paper examines the economic rationality of GPT by instructing it to make budgetary decisions in four domains: risk, time, social, and food preferences. We measure economic rationality by assessing the consistency of GPT decisions with utility maximization in classic revealed preference theory. We find that GPT decisions are largely rational in each domain and demonstrate higher rationality scores than those of humans reported in the literature. We also find that the rationality scores are robust to the degree of randomness and demographic settings such as age and gender, but are sensitive to contexts based on the language frames of the choice situations. These results suggest the potential of LLMs to make good decisions and the need to further understand their capabilities, limitations, and underlying mechanisms.
    Date: 2023–05
  8. By: David Boto-García (Universitat de les Illes Balears); Veronica Leoni (Universitat de les Illes Balears)
    Keywords: hedonic pricing, coastal amenities; capitalization effects; peer-to-peer markets; distance decay.
    Date: 2022
  9. By: Wei Tian
    Abstract: Policy evaluation in empirical microeconomics has been focusing on estimating the average treatment effect and more recently the heterogeneous treatment effects, often relying on the unconfoundedness assumption. We propose a method based on the interactive fixed effects model to estimate treatment effects at the individual level, which allows both the treatment assignment and the potential outcomes to be correlated with the unobserved individual characteristics. This method is suitable for panel datasets where multiple related outcomes are observed for a large number of individuals over a small number of time periods. Monte Carlo simulations show that our method outperforms related methods. To illustrate our method, we provide an example of estimating the effect of health insurance coverage on individual usage of hospital emergency departments using the Oregon Health Insurance Experiment data.
    Date: 2023–06

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.