nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2016‒02‒29
seven papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  2. The supply of personal information: A study on the determinants of information provision in e-commerce scenarios By Potoglou, Dimitris; Palacios, Juan; Feijoo, Claudio; Gómez Barroso, Jose-Luis
  3. Nonparametric identification of endogenous and heterogeneous aggregate demand models: complements, bundles and the market level By Fabian Dunker; Stefan Hoderlein; Hiroaki Kaido
  4. Willingness to Pay for Firm Reputation: Paying for Risk Rating in the Annuity Market By Alcalde, Pilar; Vial, Bernardita
  5. Do long-haul truckers undervalue future fuel savings? By Adenbaum, Jacob; Copeland, Adam; Stevens, John J.
  6. Assessing willingness to pay for marine and coastal ecosystems: A Case Study in Greece By Halkos, George; Galani, Georgia
  7. Heterogeneous rebound effects: Comparing estimates from discrete-continuous models By Frondel, Manuel; Martinez Flores, Fernanda; Vance, Colin

  1. By: Adriano Alessandrini (Sapienza Rome University); Paolo Delle Site (University Niccolò Cusano); Valerio Gatta (Roma Tre University); Edoardo Marcucci (Roma Tre University); Qing Zhang (Sapienza Rome University)
    Abstract: Driverless buses running in low-speed, mixed-traffic conditions are the subject of current research and demonstration in Europe. The paper aims to assess how automation fares with respect to conventional services in terms of users' attitudes. Stated preference data, based on a questionnaire administered in twelve cities, are used for the estimation of logit models providing preference shares for the conventional and the automated bus. The correlation among errors in repeated measurement data is addressed using a multivariate version of the Farlie-Gumbel-Morgenstern copula, yielding a closed form for the choice sequence probability. Estimation results show a relatively higher preference for automation across the cities where the automated bus is implemented inside a major facility. Without provision of information on how the system works and with no experience, users tend not to trust automation in the normal mixed-traffic conditions that are found in cities. The impacts of socio-economic variables are heterogenous across cities. Comparison between the logit based on the independence assumption and the logit with correlated observations shows deviations in coefficient estimates as large as twenty per cent with a typical sample size of ab out two hundred respondents and four choice tasks per individual. Deviations decrease to few percent-age points when sample size is tripled. Deviations in preference shares are, however, negligible, a result which, in terms of policy implications, is indicative of the validity of the independence assumption in applied work
    Keywords: automated bus, stated preference, logit, correlation, Farlie-Gumbel-Morgenstern copula
    Date: 2015
  2. By: Potoglou, Dimitris; Palacios, Juan; Feijoo, Claudio; Gómez Barroso, Jose-Luis
    Abstract: Disjoint research efforts have so far considered latent constructs (e.g. privacy concerns) either as an independent variable to explore consumers' actual or stated intentions or - to a less extent - as dependent variable explained through a number of antecedents (e.g. privacy awareness, demographic differences). However, there has not been a formal link across antecedents, latent constructs and behavioural (or stated) intentions in the context of ecommerce or information disclosure. This paper aims to fill this gap in the literature in order to establish a better understanding of the role of attitudes in respondents' willingness to engage in online purchases. We employ a stated preference discrete choice experiment to collect respondents' choices across online retailers, conventional store and opt-out options under different levels of personal-information requirements. Personal information in the experiment is presented across three dimensions (attributes): amount/type of information collected, duration of storage and the likelihood of this information being shared with third parties. These dimensions are introduced in order to be able to capture risks involved in online transactions according to consumer perceptions. Using the Privacy Calculus as a guiding conceptual framework, the experiment also offers respondents trade-offs between benefits such as faster check-out, detailed reviews and priority shipping of the purchased product. The choice data are complemented with a set of attitudinal indicators (psychometric scales) describing individuals’ attitudes toward information privacy protection. The data comes from 502 participants representing the online-user population in the UK. We report results from Integrated Latent Variable models, which test the influence of these latent constructs in the consumers' decision to purchase a product online and their sensitivity upon attributes describing online retailers. Preliminary model estimation results show that the higher an individual's concern, general caution and technical protection the less likely a consumer is to purchase a product online. In a joint model, the influence of privacy concern is found to outweigh the influence of general caution and technical protection. Also, consumers with increased general caution are less sensitive in the case an online retailer shares their personal data with third parties.
    Date: 2015
  3. By: Fabian Dunker (Institute for Fiscal Studies); Stefan Hoderlein (Institute for Fiscal Studies and Boston College); Hiroaki Kaido (Institute for Fiscal Studies and Boston University)
    Abstract: This paper studies nonparametric identification in market level demand models for differentiated products. We generalize common models by allowing for the distribution of heterogeneity parameters (random coefficients) to have a nonparametric distribution across the population and give conditions under which the density of the random coefficients is identified. We show that key identifying restrictions are provided by (i) a set of moment conditions generated by instrumental variables together with an inversion of aggregate demand in unobserved product characteristics; and (ii) an integral transform (Radon transform) that maps the random coefficient density to the aggregate demand. This feature is shown to be common across a wide class of models, and we illustrate this by studying leading demand models. Our examples include demand models based on the multinomial choice (Berry, Levinsohn, Pakes, 1995), the choice of bundles of goods that can be substitutes or complements, and the choice of goods consumed in multiple units.
    Date: 2014–05
  4. By: Alcalde, Pilar; Vial, Bernardita
    Abstract: In this paper we test the existence of a reputation premium in the context of the annuity market in Chile. This market provides an exceptionally good setting to measure consumers’ willingness to pay: retirees choose between a set of offers that vary only in the quote and the risk rating –a measure of the firm’s solvency– within each class of product. We find that willingness to pay for the reputation linked to the firm’s risk rating is statistically and economically significant. We also find a strong relationship between willingness to pay and intermediary choice, and we explore four potential sources of correlation between them.
    Keywords: reputation premium, willingness to pay, demand estimation, annuity markets
    JEL: D12 D53 L14
    Date: 2016–01–22
  5. By: Adenbaum, Jacob (Federal Reserve Bank of NY); Copeland, Adam (Federal Reserve Bank of NY); Stevens, John J. (Board of Governors of the Federal Reserve System (U.S.))
    Abstract: The U.S. federal government enacted fuel efficiency standards for medium and heavy trucks for the first time in September 2011. Rationales for using this policy tool typically depend upon frictions existing in the marketplace or consumers being myopic, such that vehicle purchasers undervalue the future fuel savings from increased fuel efficiency. We measure by how much long-haul truck owners undervalue future fuel savings by employing recent advances to the classic hedonic approach to estimate the distribution of willingness-to-pay for fuel efficiency. We find significant heterogeneity in truck owners' willingness to pay for fuel efficiency, with the elasticity of fuel efficiency to price ranging from 0.51 at the 10th percentile to 1.33 at the 90th percentile, and an average of 0.91. Combining these results with estimates of future fuel savings from increases in fuel efficiency, we find that long-haul truck owners' willingness-to-pay for a 1 percent increase in fuel efficiency is, on average, just 29.5 percent of the expected future fuel savings. These results suggest that introducing fuel efficiency standards for heavy trucks might be an effective policy tool to raise medium and heavy trucks' fuel economy.
    Keywords: fuel efficiency standards; durable goods; discrete-choice demand estimation
    JEL: D22 L51 L92
    Date: 2015–12–29
  6. By: Halkos, George; Galani, Georgia
    Abstract: The achievement of good environmental status (GES) of marine and coastal ecosystem services is specified in the Marine Strategy Framework Directive (MSFD). This paper uses the choice experiment methodology (CE) to estimate the value of non-market benefits of marine and coastal ecosystem. Non-market benefits are rarely considered in marine planning and management. Assessing respondents’ willingness to pay in order to contribute in the development of marine planning and management implies that changes in marine and ecosystem services in Greece should be considered. Using appropriate econometric methods the empirical results show government trust and willingness to pay is directly linked. The results demonstrate also that preferences are heterogeneous with changes in certain marine and coastal attributes.
    Keywords: Marine Strategy Framework Directive; Marine and coastal ecosystems; Non-market valuation; Choice experiment.
    JEL: C1 C25 Q50 Q51 Q57
    Date: 2016–01–11
  7. By: Frondel, Manuel; Martinez Flores, Fernanda; Vance, Colin
    Abstract: Discrete-continuous models have become a common technique for addressing selectivity biases in data sets with endogenously partitioned observational units. Alternative two-stage approaches have been suggested by LEE (1983), DUBIN and MCFADDEN (1984), and DAHL (2002), all of which capture the first-stage discrete choice by the multinomial logit model, while the second-stage outcome equation is estimated using OLS. The nonlinearity introduced by the selection bias correction implies that the second-stage coefficients cannot be interpreted as marginal effects. Instead, the marginal effects are obtained using the estimates from both the first and second stages, a step that has been widely neglected in the applied literature. After deriving formulae for the marginal effects obtained from these selection correction approaches, we estimate a joint model of automobile ownership and distance driven to quantify the rebound effect, the behaviorally induced increase in driving that results from higher fuel economy. Our example illustrates that the pattern of rebound effects varies substantially depending on the method of selection bias correction.
    Abstract: Diskret-stetige Modelle sind zu einer gängigen Methode geworden, um mit Selektionsverzerrungen in Datensätzen mit endogen partitionierten Beobachtungseinheiten umzugehen. LEE (1983), DUBIN und MCFADDEN (1984) und DAHL (2002) schlugen dafür verschiedene zweistufige Ansätze vor. Dabei wird die auf der ersten Stufe getroffene diskrete Entscheidung zum Automobilbesitz mit einem multinomialen Logit-Modell spezifiziert und die zweite Stufe wird mit der Methode der kleinsten Quadrate geschätzt. Die marginalen Effekte ergeben sich als eine nichtlineare Kombination aus den Koeffizienten der ersten und der zweiten Stufe, ein Fakt, der von der angewandten Literatur größtenteils vernachlässigt wird. Nach der mathematischen Herleitung der Formeln für die marginalen Effekte, die aus diesen Ansätzen zur Korrektur der Selektionsverzerrung gewonnen werden, wird ein gemeinsames Modell des Automobilbesitzes und der Fahrleistung geschätzt, um damit den Rebound-Effekt zu schätzen. Dieser beschreibt die Zunahme der Fahrleistung als Folge effizienterer Kraftstoffnutzung. Es zeigt sich, dass die Größe der Rebound-Effekte je nach der zur Korrektur der Selektionsverzerrung angewandten Methode erheblich variiert.
    Keywords: discrete-continuous models,marginal effects,car use
    JEL: D12 Q21 Q41
    Date: 2016

This nep-dcm issue is ©2016 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.