nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2017‒10‒29
five papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. A Monte Carlo Evaluation of the Logit-Mixed Logit under Asymmetry and Multimodality By Riccardo Scarpan; Cristiano Franceschinis; Mara Thiene
  2. Essays on the demand for ethanol in the United States: willingness to pay for E85 By Liao, Kenneth
  3. BIG SCIENCE, LEARNING AND INNOVATION: EVIDENCE FROM CERN PROCUREMENT By Anna Giunta; Massimo Florio; Francesco Giffoni; Emanuela Sirtori
  4. Institutional determinants of protest responses in stated preference studies By Victor Champonnois
  5. Rational Filters By Hassan Nosratabadi

  1. By: Riccardo Scarpan (University of Waikato); Cristiano Franceschinis (University of Padova); Mara Thiene (University of Padova)
    Abstract: The recently introduced (Train 2016) logit-mixed logit (LML) model is a key advancement in choice modelling: it generalizes many previous parametric and semi-nonparametric methods to represent taste heterogeneity for bundled nonmarket goods and services. We report results from Monte Carlo experiments designed to assess performance across workable sample sizes and to retrieve data-driven random coefficients distributions in the three variants of the LML model proposed in the seminal paper. Assuming a multi-modal data generating process, with a panel of four and eight choices per respondent, we compare the performance of WTP-space LML models with conventional parametric model specifications based on the Mixed logit model with normals (MXL-N) in preference and WTP space. Results are encouraging and support the adoption of flexible LML specifications with a high number of parameters as they seem to do better, but only at large enough sample sizes. To explore the saliency of the Monte Carlo results in an empirical application, we use data obtained from a discrete choice experiment to derive preferences for tap water quality in the province of Vicenza (northern Italy). LML models retrieve multimodal and asymmetric distributions of marginal WTPs for water quality attributes. Results show not only how the shape of such distributions vary across tap water attributes, but also the importance of being able to uncover them, considering that they would be hidden when using the MNL-N.
    Keywords: logit-mixed logit; flexible taste distributions; panel random utility models
    Date: 2017–10–24
  2. By: Liao, Kenneth
    Abstract: This dissertation contains three studies that estimate the distribution of willingness to pay (WTP) for E85 as a substitute for E10 among flex motorists in the United States. The results are vital for estimating the demand for ethanol beyond the blend wall and for analysis of the Renewable Fuel Standard. The first study attempts to estimate the distribution of preference for E85 from data generated by a survey of E85 stations in Minnesota. The study uses an extensive sample of recent observations, but estimates of the WTP distribution vary substantially depending on model specification. The conclusion is that the data are not suitable to estimate the distribution of WTP for E85.The second and third studies collect primary data from E85 stations in different regions of the United States to more accurately estimate preferences for E85 and investigate locational differences. The studies obtain revealed-preference (RP) data from flex motorists refueling at E85 stations and stated-preference (SP) data from surveying the flex motorists and presenting hypothetical scenarios. The second study uses the RP data to estimate relative preferences for E85, and the third study incorporates the SP data to better capture the wide range of fuel-switching behavior.The estimation sample consists of about nine hundred flex motorists in six urban areas in the Midwest and California. The sample of flex motorists who refuel at E85 stations is endogenously stratified; the probability of a flex motorist appearing in the sample is correlated to the motorist's WTP for E85. The models apply corrective probability weights so estimates reflect the population and not the sample.The results show that a $0.10 increase in the E85-E10 price difference decreases the probability of motorists choosing E85 by about 2.5 percent, on average, and preferences are spread over a broad range of fuel prices. In general, motorists are willing to pay more for E85 in California than in the Midwest, and when E85 and E10 are priced equally on a cost-per-mile basis, about 25 percent of flex motorists choose E85 in the Midwest compared to 75 percent in California.
    Date: 2016–01–01
  3. By: Anna Giunta; Massimo Florio; Francesco Giffoni; Emanuela Sirtori
    Abstract: We study the way in which public procurement by big research infrastructures enhances suppliers’ performance. Using survey data on 669 CERN suppliers, we built a unique data set to analyse, through an ordered logit model and Bayesian networks, the determinants of suppliers’ sales, profits and development activities. We find that collaborative relations between CERN and its suppliers improve suppliers’ performance and increase positive spill overs along the supply chain. This suggests that public procurement for innovation policies should promote cooperative relations and not only market mechanisms.
    Keywords: Big Science, Public Procurement, CERN, Suppliers
    JEL: O31 O33 O38 C11
    Date: 2017–10
  4. By: Victor Champonnois (AMSE)
    Abstract: In stated preference surveys, institutional context is often found to be an important determinant of protest responses. However, the very same institutional context does not change within one survey, enabling no strong conclusion about its effect on the protest behavior. Moreover, although the importance of the institutional context on the choice of a payment vehicle has been suspected, no study is specifically devoted to the way their interaction affects the protest rate. This paper tries to fill these gaps by relying on meta-data on stated preference studies for environmental goods along with institutional variables at the country level. Results show that institutional variables are significant determinants of the protest rates, but there is no significant evidence to suggest that the choice of a payment vehicle affects differently the probability of protesting depending on the institutional context.
    Keywords: Institutions, Protest responses
    JEL: Q51
    Date: 2017–10
  5. By: Hassan Nosratabadi (Rutgers, The State University Of New Jersey)
    Abstract: It has been widely documented that reference points influence the choice. If references affect choice by attracting attention towards an alternative, what can be said about the joint effect of the references? Assuming that references form preferences, or are rational filters, this paper extracts a reference-dependent choice model with joint referential effects from WARP. Assume that a DM has an ''unfiltered'' pairwise preference which is inferred from her choice over doubletons. The DM's uses her rational filters consecutively on the pairwise preference in order to finalize her choice.
    Keywords: Rational Preferences, Rational Filters, Revealed Preference, Referential Decision Maker, WARP Decompositions
    JEL: D11 D81
    Date: 2017–10–20

This nep-dcm issue is ©2017 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.