nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2023‒01‒16
seven papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. COVID19 and the Value of Non-Monetary Job Attributes to Women:Evidence from A Choice Experiment in Egypt By Rana Hendy; Shaimaa Yassin
  2. Identification of time-varying counterfactual parameters in nonlinear panel models By Irene Botosaru; Chris Muris
  3. Accounting for subsistence needs in non-market valuation: a simple proposal By Victor Champonnois; Olivier Chanel
  4. Omitted budget constraint bias in discrete-choice demand models By Pesendorfer, Martin; Schiraldi, Pasquale; Silva-Junior, Daniel
  5. Estimating Latent-Variable Panel Data Models Using Parameter-Expanded SEM Methods By Siqi Wei
  6. Valuing Water Service Improvements through Revealed Preference: Averting Behaviour Method By Rajapakshe, Sisira; Termansen, Mette; Paavola, Jouni
  7. A Better Test of Choice Overload By Mark Dean; Dilip Ravindran; J\"org Stoye

  1. By: Rana Hendy (American University in Cairo); Shaimaa Yassin (Institute for Research on Public Policy, Canada)
    Abstract: Boosting low levels of female labor force participation remains a challenge in the MENA region. Women, especially after marriage and childbirth, typically forgo the labor market (LM), particularly when jobs/job offers are non-family-friendly. Especially for females, a job is perceived as a combined package of wages and non-monetary attributed. This paper relies on an attributebased discrete choice experiment using hypothetical job offers, as opposed to the employment situation pre and post the outbreak of the Coronavirus. The objective is to estimate the willingness to pay (WTP) distribution for non-monetary job attributes. An experiment was administered within a COVID-19 impact survey in Egypt (namely CETUS20) - 5 months into the outbreak of the pandemic, making it possible to measure the change in job preferences following the COVID19 health shock. The hypothetical choice method robustly identifies preferences, and overcomes challenges to estimate WTP for specific non-monetary job attributes using other methods. Our findings reveal that COVID-19 has led workers to value more positive job amenities, such as parttime jobs, flexible work, work from home and shorter commutes. With the increased burden of domestic work, females with children value the most jobs where they can work on a part-time basis. They would require to receive substantial increases to their current labor income to accept jobs with a non-family friendly set-up, such as the need to work in weekends or night-shifts. Interestingly, however, respondents in the experiment, particularly male workers, have perceived overtime as a positive job amenity. Their WTP for the latter increased post-COVID suggesting income challenges faced by workers post-COVID. Generally, a substantial proportion of our experiment's employed respondents accept the hypothetical job offers they receive during the interview (about 40% of the males and 70% of the females). More than 50% of those who accepted those offers would have never accepted them prior to COVID. Our results reveal the change in the value of employment to workers, particularly females, which comprises both the wage and the non-monetary attributes associated with employment
    Date: 2022–09–20
  2. By: Irene Botosaru; Chris Muris
    Abstract: We present identification results for counterfactual parameters in a class of nonlinear semiparametric panel models with fixed effects and time effects. This class accommodates both discrete and continuous outcomes and discrete and continuous regressors, and includes the binary choice model with two-way fixed effects, the ordered choice model with time-varying thresholds, the censored regression model with time-varying censoring, and various transformation models for continuous dependent variables. We show that the survival distribution of counterfactual outcomes is identified (point or partial) in this class of models. This parameter is a building block for most partial and marginal effects of interest in applied practice that are based on the average structural function as defined by Blundell and Powell (2003, 2004). Our main results focus on static models, with a set of results applying to models without any exogeneity conditions. Our results do not require parametric assumptions on the distribution of the error terms and do not require time-homogeneity on the outcome equation. To the best of our knowledge, ours are the first results on average partial and marginal effects for binary choice and ordered choice models with fixed effects, time effects, and non-logistic errors.
    Date: 2022–12
  3. By: Victor Champonnois (UMR G-EAU - Gestion de l'Eau, Acteurs, Usages - Cirad - Centre de Coopération Internationale en Recherche Agronomique pour le Développement - IRD - Institut de Recherche pour le Développement - AgroParisTech - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement - Institut Agro - Montpellier SupAgro - Institut Agro - Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement); Olivier Chanel (AMSE - Aix-Marseille Sciences Economiques - EHESS - École des hautes études en sciences sociales - AMU - Aix Marseille Université - ECM - École Centrale de Marseille - CNRS - Centre National de la Recherche Scientifique)
    Abstract: Revealed and stated preference techniques are widely used to assess willingness to pay (WTP) for non-market goods as input to public and private decision-making. However, individuals first have to satisfy subsistence needs through market good consumption, which affects their ability to pay. We provide a methodological framework and derive a simple ex post adjustment factor to account for this effect. We quantify its impacts on the WTP for non-market goods and the ranking of projects theoretically, numerically and empirically. This confirms that non-adjusted WTP tends to be plutocratic: the views of the richest – whatever they are – are more likely to impact decision-making, potentially leading to ranking reversal between projects. We also suggest that the subsistence needs-based adjustment factor we propose has a role to play in value transfer procedures. The overall goal is a better representation of the entire population's preferences with regard to non-market goods.
    Keywords: subsistence needs,adjustment factor,non-market valuation,value transfer,population’s preferences
    Date: 2022
  4. By: Pesendorfer, Martin; Schiraldi, Pasquale; Silva-Junior, Daniel
    Abstract: A large body of discrete-choice demand studies estimate a demand model in which the consumer’s budget constraint is not taken into account. We illustrate how incorrectly specifying the consideration set, when in fact the budget constraint binds for some products, may bias the demand estimates. We illustrate and quantify the nature of the bias in three ways: (i) in analytical examples; (ii) in field data commonly used in the literature and (iii) in a Monte Carlo study. We find that the price sensitivity can be substantially lower when correctly imposing the budget constraint, and own-price elasticities are typically overestimated although the direction of the own-price elasticity bias is in general ambiguous and depends on the income distribution.
    Keywords: omitted budget constraint bias; discrete choice demand; automobile inustry; Elsevier deal
    JEL: D10 D40 L10 L62
    Date: 2023–01–01
  5. By: Siqi Wei (CEMFI, Centro de Estudios Monetarios y Financieros)
    Abstract: The Expectation-Maximization (EM) algorithm is a popular tool for estimating models with latent variables. In complex models, simulated versions such as stochastic EM, are often implemented to overcome the difficulties in computing expectations analytically. A drawback of the EM algorithm and its variants is the slow convergence in some cases, especially when the models contain high-dimensional latent variables. Liu et al., 1998 proposed a parameter-expanded algorithm (PX-EM) to speed up convergence. This paper explores the potential of parameter expansion ideas for estimating nonlinear panel models using the stochastic EM algorithm. We develop PX-SEM methods for two types of nonlinear panel data models: 1) binary choice models with individual effects and persistent shocks, and 2) persistent-transitory dynamic quantile processes. We find that PX-SEM can greatly speed up convergence especially when the initial guess is relatively far away from true values.
    Keywords: Stochastic EM, parameter-expansion, discrete choice model, dynamic quantile regression, latent variables.
    JEL: C13 C33 C63
    Date: 2022–07
  6. By: Rajapakshe, Sisira; Termansen, Mette; Paavola, Jouni
    Abstract: Access to quality and adequate water supply is a basic need to sustain human life. Health risk of unsafe drinking water is a serious issue in many poor and underserved communities in developing countries. Therefore, the improvements of the health status of the people are considered as one of the main justifications of promoting investment in water infrastructure. People take a number of coping strategies for water service improvement and the expenditures on such measures implicitly reflect their preferences for water service improvements. This paper leads to estimation of the benefits of water service improvements using the Averting Expenditure Method. This study examines the determinants of averting actions and the prevailing health impacts using the Probit models aiming to examine why some households practice averting measures and have experienced with health impacts while others not. Study found that the respondent’s socio-economic attributes significantly determine the choice of averting behaviours. Then this study calculates the monitory values of number of averting measures and it was found that the mean averting expenditures of the household are Rs. 577 and Rs,. 740 per month respectively the households connected to the system and un-connected to the system. piped households spending an average about Rs. 500 per month as a damage cost of water related health impacts which is unseen but part of the real cost of lack of access to good quality water supply. Study conclude that the WTP estimates are much higher than the payments for existing piped schemes hence cost of clean and consistent water supply could be finance through a user payment scheme.
    Keywords: Water quality, health impacts, averting behaviors, averting expenditures, willingness to pay.
    JEL: Q51
    Date: 2022–12–11
  7. By: Mark Dean; Dilip Ravindran; J\"org Stoye
    Abstract: Choice overload - by which larger choice sets are detrimental to a chooser's wellbeing - is potentially of great importance to the design of economic policy. Yet the current evidence on its prevalence is inconclusive. We argue that existing tests are likely to be underpowered and hence that choice overload may occur more often than the literature suggests. We propose more powerful tests based on richer data and characterization theorems for the Random Utility Model. These new approaches come with significant econometric challenges, which we show how to address. We apply our tests to new experimental data and find strong evidence of choice overload that would likely be missed using current approaches.
    Date: 2022–12

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.