nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2020‒11‒23
six papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. Values of Time for Carpool Commuting with HOV lanes: A Discrete Choice Experiment in France By Alix Le Goff; Guillaume Monchambert; Charles Raux
  2. Choice Preferences for Regional and Green Electricity: Influence of Regional and Environmental Identity By Fait, Larissa; Wetzel, Heike; Groh, Elke D.
  3. What drives the location choice of new manufacturing plants in Germany? By Krenz, Astrid
  4. Attention, recall and purchase: Experimental evidence on online news and advertising By Andre Veiga; Tommaso Valletti
  5. I spot, I adopt! Peer effects and visibility in solar photovoltaic system adoption of households. By Rode, Johannes; Müller, Sven
  6. Relaxing Conditional Independence in an Endogenous Binary Response Model By Alyssa Carlson

  1. By: Alix Le Goff (LAET - Laboratoire Aménagement Économie Transports - UL2 - Université Lumière - Lyon 2 - ENTPE - École Nationale des Travaux Publics de l'État - CNRS - Centre National de la Recherche Scientifique); Guillaume Monchambert (LAET - Laboratoire Aménagement Économie Transports - UL2 - Université Lumière - Lyon 2 - ENTPE - École Nationale des Travaux Publics de l'État - CNRS - Centre National de la Recherche Scientifique); Charles Raux (LAET - Laboratoire Aménagement Économie Transports - UL2 - Université Lumière - Lyon 2 - ENTPE - École Nationale des Travaux Publics de l'État - CNRS - Centre National de la Recherche Scientifique)
    Abstract: We conduct a discrete choice experiment on 931 solo-driving commuters in Lyon, France to estimate the values of end-to-end travel time (VoTT) in the presence of an HOV lane for four modes: Solo Driver, Carpool Driver, Carpool Passenger and Public Transport. Mixed and latent class logit models are estimated. We find that Carpool Passenger, Carpool Driver and Public Transport median VoTTs are respectively around 20%, 40% and 60% higher than Solo Driver VoTT. The analysis of individual heterogeneity distinguishes three classes of behavior in our sample: open to carpool as a driver (41%), open to passenger modes (32%) and resistant to all alternatives to solo driving (28%). These three categories allow to identify solo drivers who could switch to carpool as drivers. We show that encouraging current solo drivers to switch to carpool as passengers will be more sensitive if public transport services are also improved.
    Keywords: HOV-lane,Commuting Trips,Carpool,Values of Time,Discrete Choice Experiment,Working Papers du LAET
    Date: 2020
  2. By: Fait, Larissa; Wetzel, Heike; Groh, Elke D.
    Abstract: The success of the energy transition is important in order to limit climate change and its consequences. However, the expansion of renewables faces several challenges. In particular, there is growing resistance to renewable projects at the local level. Therefore, we examine preferences for regionally produced green electricity as a way to increase acceptance. In addition, we investigate whether regional or environmental identity have an influence on these preferences. Therefore, we analyse data from a choice experiment conducted with 672 regional consumers in Germany. The sample is divided into 3 subgroups that face different priming treatments in order to determine the effects of identity salience. Our results show that, in addition to a green electricity mix, consumers have positive preferences for regional aspects of electricity contracts, such as the regional production or the regional ties of electricity suppliers. Moreover, respondents who were primed with their regional or environmental identity show a significantly higher willingness to pay for these attributes. While the priming for environmental identity strengthens the existing preferences, the regional priming seems to influence the underlying decision heuristics. Overall, our findings indicate that there is a clear preference for regional electricity and therefore it would be reasonable for electricity providers to offer regional electricity. Environmental and regional aspects should be emphasised in marketing, as these can have a significant impact on electricity contract choice.
    JEL: C25
    Date: 2020
  3. By: Krenz, Astrid
    Abstract: Almost 30 years after German reunification, a persistent gap in different firm performance measures exists between East and West Germany. In this paper I focus on the differences in new German manufacturing plants' location choices across the German district-free cities and districts and investigate its regional determinants. For that purpose, I construct a novel, rich regional- and plant-level dataset based on the Official Firm Statistics from the German Federal Statistical Office and the Offices of the Laender. The analysis provides first-time evidence regarding how in particular the location decision of plants in the German economy is in uenced by regional road infrastructure as well as regional structural funding. The effects are economically important and significant. The results reveal that a 10 percent increase in plant agglomeration increases the odds of a new plant to locate in the region by 12 percent. A 10 percent decrease of travel time on roads increases the odds of a plant to locate by 4 percent in Germany overall, by 7.6 percent among East German regions and by 26.5 percent in particular for large plants in the East German regions. A 10 percent larger population increases the odds to locate by 8.7 percent. A 10 percent increase in regional structural funding for infrastructure purposes increases the odds to locate in a region in East Germany by 8.3 percent in particular for large plants. Policy implications emerge that address in particular the improvement of infrastructure and support to reap the benefits that arise from agglomeration externalities.
    Keywords: Firm location choice,regional road infrastructure,Germany,agglomeration economies,regional structural funding,East-West gap,conditional logit,nested logit.
    JEL: D22 L25 R11 R12
    Date: 2020
  4. By: Andre Veiga (Imperial College London); Tommaso Valletti (Imperial College London)
    Abstract: We conduct an experiment where 1,000 individuals read online news articles and are shown ads for branded goods next to those articles. Using eye-tracking technology, we measure the attention that each individual devotes to reading each article and viewing each ad. Then, respondents choose between cash or vouchers for branded goods. We find that attention is a predictor both of willingness-to-pay for brands, and for brand recall. We also give suggestive evidence of the main drivers of attention. These include the type of news, and the match between individual political preferences and the media outlet.
    Keywords: Online Advertising, Experiments, Attention, E-commerce, Targeting
    JEL: M37 C91 L86
    Date: 2020–10
  5. By: Rode, Johannes; Müller, Sven
    Abstract: We study variation of peer effects in rooftop photovoltaic adoption by households. Our investigation employs geocoded data on all potential adopters and on all grid-connected photovoltaic systems set up in Germany through 2010. We construct an individual measure of peer effects for each potential adopter. For identification, we exploit exogenous variation in two dimensions of photovoltaic system roof appropriateness of neighbors: their inclination and their orientation. Using discrete choice models with panel data, we find evidence for causal peer effects. However, the impact of one previously installed PV system on current adoption decreases over time. We also show that visible PV systems cause an increase in the odds of installing which is up to three times higher in comparison to all PV systems. At rural locations visibility may be less important, which indicates that word-of-mouth communication plays a stronger role.
    Keywords: Causal peer effects,installed base,discrete choice,technology adoption and diffusion,solar photovoltaic panels,visibility
    JEL: O33 C35 Q55 R10
    Date: 2020
  6. By: Alyssa Carlson (Department of Economics, University of Missouri-Columbia)
    Abstract: For binary response models, the literature primarily addresses endogeneity by a control function approach assuming conditional independence (CF-CI). However, as the literature also notes, CF-CI implies conditions like homoskedasticity (of the latent error with respect to the instruments) that fail in many empirical settings. I propose an alternative approach that allows for heteroskedasticity, achieving identification with a conditional mean restriction. These identification results apply to a latent Gaussian error term with flexibly parametrized heteroskedasticity. I propose a two-step conditional maximum likelihood estimator and derive its asymptotic distribution. In simulations, the new estimator outperforms others when CF-CI fails and is fairly robust to distributional misspecification. An empirical illustration studies married women's labor force participation.
    Keywords: Binary choice model, Endogenous regressors, Control function, Heteroskedasticity
    JEL: C31 C35
    Date: 2020–09

This nep-dcm issue is ©2020 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.