nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2026–11–16
eight papers chosen by
Edoardo Marcucci, Università degli studi Roma Tre


  1. Consumer Willingness to Pay for Climate-Smart Wheat By Sanderson, Kim; Dodds, Kaylee; Hobbs, Jill; Tyack, Nicholas
  2. A utility-based framework for measuring perceived job accessibility using destination-mode choice models By Siqueira, Matheus Fontenelle; Loureiro, Carlos Felipe Grangeiro
  3. Estimation of Rational Inattention--Additive Random Utility Models By Ruolei Zhu
  4. Linear Demand Systems are Consistent with Discrete Choice By Afonso Rodrigues
  5. Whose values does the HDI reflect? Evidence from a discrete choice experiment in Tanzania By Shaun Da Costa;; Koen Decancq;
  6. Entry Motivations Shape Preferences for Social Protection Among Platform Workers By Zuzanna Kowalik; Piotr Lewandowski; Fabrizio Pompei; Holger Stichnoth; Wojciech Szymczak; Laurène Thil
  7. Money, Time, and the Demand for Children By Evie Thompson; Guy Michaels
  8. Online Bayesian Inference for a Dirichlet Process Mixture of Binary Logit Models By Hajime Watanabe; Charisma F. Choudhury; Stephane Hess

  1. By: Sanderson, Kim; Dodds, Kaylee; Hobbs, Jill; Tyack, Nicholas
    Keywords: Consumer/Household Economics
    Date: 2026
    URL: https://d.repec.org/n?u=RePEc:ags:activa:417317
  2. By: Siqueira, Matheus Fontenelle; Loureiro, Carlos Felipe Grangeiro
    Abstract: Perceived accessibility has become a central concept in accessibility research, but it is usually measured with psychometric scales, which are not decomposed into the components of accessibility, cannot be recomputed for new scenarios and carry no welfare interpretation. This paper argues that perceived accessibility can be measured with the expected maximum utility (logsum) of a discrete choice model whose choice set represents the alternatives the individual can use and knows, and whose valuations and perception of opportunities are estimated from behavior rather than imposed. The argument is developed from the mechanisms through which calculated and perceived accessibility diverge and applied to home-to-work travel of low-income workers in Fortaleza, Brazil, with a stated and revealed preference survey collected in 2024. The experiment screened the modes presented to each respondent by resources, distance and habitual use, so that the choice set reflects individual availability and awareness. Within a hierarchical structure, a mixed logit mode choice model estimated jointly on stated and revealed choices supplies a mode logsum for every zone, and a destination choice model with a random parameter estimates how the formal job mass is perceived. The measure contains the gravity measure as a restricted case, but estimates the trade-off between attractiveness and impedance, represents heterogeneous perceptions and multimodal availability, and carries a welfare interpretation. Valuations of time differ little between four gender and income strata, whereas the perception of job opportunities is strongly heterogeneous within each stratum. The resulting measure is individual, evaluative, awareness-conditioned and suitable for appraisal.
    Date: 2026–10–20
    URL: https://d.repec.org/n?u=RePEc:osf:socarx:xrtwd_v1
  3. By: Ruolei Zhu
    Abstract: This paper develops likelihood-based estimation for parametric rational inattention--additive random utility models. We establish consistency and asymptotic normality of the exact maximum likelihood estimator and provide conditions under which the simulated estimator shares its asymptotic distribution. To implement estimation, we develop Newton--BA, a KKT-guided hybrid of Newton--Raphson and Blahut--Arimoto (BA). The algorithm accommodates both interior and boundary solutions and substantially improves computational efficiency relative to direct BA while preserving numerical accuracy. Monte Carlo simulations show that parameter recovery improves with sample size and that confidence-interval coverage is generally close to the nominal $95$ percent level. Finally, we compare our model with no- and perfect-information logit benchmarks in an empirically calibrated ModeCanada experiment. Our model achieves similar in-sample likelihood fit to perfect-information logit but more accurately recovers key preference parameters, choice probabilities, and responses to travel-time changes.
    Date: 2026–10
    URL: https://d.repec.org/n?u=RePEc:arx:papers:2610.16701
  4. By: Afonso Rodrigues
    Abstract: Aggregate linear demand systems can be micro-founded by a population of heterogeneous consumers making discrete choices. They can also be extended to incorporate income effects. I prove these results and show how to structurally estimate this class of models using only market-level data. The distribution of consumer preferences is recovered by disciplining the corner solutions with aggregate terms only. This approach allows for the same richness of Berry, Levinsohn, and Pakes (1995) [BLP] while retaining the analytical and computational advantages of linear demand: it does not require exogenously fixing market size, allows for heterogeneity in choice sets, and results in a flexible substitution matrix which varies endogenously as different consumers enter/exit the market. The discrete-choice microfoundation facilitates welfare analysis and the flexible measurement of markups an cost pass-throughs, among a wide range of other applications.
    Date: 2026–10
    URL: https://d.repec.org/n?u=RePEc:arx:papers:2610.13785
  5. By: Shaun Da Costa;; Koen Decancq;
    Abstract: Multidimensional development indices such as the Human Development Index (HDI) embed value judgements about trade-offs between dimensions. Yet these are rarely tested against the valuations of the people they describe. We use a pictogram-assisted discrete choice experiment with 361 respondents in Tanzania’s Dodoma region to elicit trade-offs between income, schooling, and life expectancy. We estimate preferences using the 264 respondents who make compensatory choices and compare their valuations with the equal-weight trade-offs embedded in the HDI. The typical respondent values an additional year of schooling more highly than an additional year of life expectancy, consistent with the HDI’s qualitative ranking of dimensions. However, the implied schooling-life expectancy value ratio is around 1.5, compared with 7.2 under the HDI at Tanzania’s observed achievement levels. Allowing for observed and unobserved preference heterogeneity reveals substantial variation in valuations across respondents, which provides little support for treating any single weighting scheme as representative of this population’s valuations. The results show that the value judgements embedded in multidimensional indices can be tested empirically, and that even in a small, geographically concentrated sample the trade-offs implied by the HDI differ markedly from respondents’ valuations.
    Date: 2026–10
    URL: https://d.repec.org/n?u=RePEc:hdl:wpaper:2604
  6. By: Zuzanna Kowalik; Piotr Lewandowski; Fabrizio Pompei; Holger Stichnoth; Wojciech Szymczak; Laurène Thil
    Abstract: We study platform workers' preferences for social protection — in the form of sick pay and paid annual leave — distinguishing between workers who entered platform work out of economic necessity (the "pushed") and those attracted by its flexibility and advantages (the "pulled"). Using a discrete-choice experiment administered to nearly 800 taxi, delivery, and cleaning platform workers in Germany, Italy, and Poland, we find an average willingness to pay at 3.7% of earnings for sick pay coverage and 4.6% for paid annual leave. Preferences, however, differ sharply by motivation: pushed workers are willing to forgo on average 5.3% of earnings for sick pay, and 5.6% for paid annual leave, while pulled workers' valuations are substantially lower (3.1% and 4.2%, respectively). This difference is most pronounced among workers without access to these benefits, suggesting that the absence of protections is particularly consequential for those who entered platform work under greater economic constraint. The findings indicate that the welfare impact of extending social protections to platform workers — as proposed by the EU Platform Work Directive — might depend on the share of necessity-driven workers in the platform workforce.
    Keywords: platform work, willingness to pay, discrete choice experiment, social protection, job quality
    JEL: J32 J28 J81
    Date: 2026
    URL: https://d.repec.org/n?u=RePEc:ulp:sbbeta:2026-38
  7. By: Evie Thompson; Guy Michaels
    Abstract: US fertility has fallen well below replacement, even as stated fertility ideals have not. We ask how much money and time women are willing to trade off for additional children, a question that is difficult to answer using observational data or even natural experiments. We field a discrete choice experiment in which 1, 995 women choose between hypothetical futures varying the number of additional children, household income, and time use. Demand falls with both income and time prices, and rises with income faster than proportionally, consistent with larger families being a luxury good. Exploratory results show that full-time work, but not part-time work, is perceived as costly, and that baseline demand varies considerably by age, religiosity, and desired fertility even as price responses vary less. Notably, women on average require compensation, often significant, to accept a second additional child, including many who say they want two more. This finding complicates the standard reading of a stated ideal of two children as evidence of unmet demand: once its price is held fixed, we find little demand to reach it.
    Keywords: fertility, gender, discrete choice experiment, time use, willingness to pay
    JEL: J13 J16 J22
    Date: 2026
    URL: https://d.repec.org/n?u=RePEc:ces:ceswps:_13124
  8. By: Hajime Watanabe; Charisma F. Choudhury; Stephane Hess
    Abstract: Flexible travel behaviour models for preference heterogeneity have largely remained within the batch-estimation paradigm. The growing availability of continuously collected behavioural data, for example from smartphone applications, highlights the need for methods that update posterior inference on such heterogeneity as new observations arrive. This study proposes an online Bayesian inference method for a Dirichlet process mixture of binary logit models. The main challenge is to update the posterior as observations arrive while allowing the latent cluster structure to expand and historical cluster assignments to be revised. We develop a sequential Monte Carlo sampler using a sequence of P\'olya--Gamma-augmented partial-data posteriors, local particle-weight corrections, and recursively maintained sufficient statistics. Each observation's contribution can be added, removed, or replaced in these summaries, supporting both sequential coefficient updating and rejuvenation that revisits historical cluster assignments. The simulation study shows that observation-by-observation sequential updating yields final posterior summaries close to those obtained by batch Markov chain Monte Carlo. Sensitivity analyses further demonstrate trade-offs between posterior approximation accuracy and computational cost as the number of particles and rejuvenation settings are varied. An illustrative empirical application shows how the method tracks posterior evolution and produces observation-specific provisional posterior summaries with low latency as real-world trip records are processed sequentially. The proposed approach provides a methodological foundation for online inference in travel behaviour models with parameter heterogeneity and for future extensions to richer choice structures, low-latency decision support, and online anomaly screening.
    Date: 2026–11
    URL: https://d.repec.org/n?u=RePEc:arx:papers:2611.06266

This nep-dcm issue is ©2026 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 https://nep.repec.org. For comments please write to the director of NEP, Marco Novarese at <director@nep.repec.org>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the Griffith Business School of Griffith University in Australia.