nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2019‒06‒24
twelve papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. Role of information in the valuation of unfamiliar goods—the case of genetic resources in agriculture By Annika Tienhaara; Heini Ahtiainen; Eija Pouta; Mikołaj Czajkowski
  2. Relationship between wine-evoked emotions and consumers’ preferences and willingness to Pay By Rahmani, Djamel; Loureiro, Maria; Escobar, Cristina; Gil, Jose Maria
  3. Modelling Consumers’ Preference and Willingness To Pay For Organic Amaranth and Tomato in Ondo State, Nigeria: Evidence From a Choice Experiment By Akinwehinmi, Oluwagbenga; Amos, Taiwo; Ogundari, Kolawole
  4. Equilibrium trade in automobile markets By Kenneth Gillingham; Fedor Iskhakov; Anders Munk-Nielsen; John Rust; Bertel Schjerning
  5. Mission of the company, prosocial attitudes and job preferences: a discrete choice experiment By Arjan Non; Ingrid Rohde; Andries de Grip; Thomas Dohmen
  6. Examining generational preferences for sustainability attributes of wine: a discrete choice experiment in California By Tait, Peter; Saunders, Caroline; Dalziel, Paul; Rutherford, Paul; Driver, Timothy
  7. One-off subsidies and long-run adoption – Experimental evidence on improved cooking stoves in Senegal By Bensch, Gunther; Peters, Jörg
  8. Consumer Demand for Ethical Products and the Role of Cultural Worldviews: The Case of Direct-Trade Coffee By Paul Hindsley; David M. McEvoy; O. Ashton Morgan
  9. Does the new "Green Architecture" of the CAP provide a chance for the conservation of Lapwings (Vanellus vanellus)? Findings from discrete choice experiments with German arable farmers By Buschmann, Christoph; Röder, Norbert
  10. Farmers’ preferences for grassland restoration: Evidence from France By Ben-Othmen, Marie Asma; Ostapchuk, Mariia
  11. Posterior Average Effects By St\'ephane Bonhomme; Martin Weidner
  12. Mission of the company, prosocial attitudes and job preferences: a discrete choice experiment By Paul Belleflamme; Martin Peitz

  1. By: Annika Tienhaara (Natural Resources Institute Finland (Luke)); Heini Ahtiainen (Natural Resources Institute Finland (Luke)); Eija Pouta (Natural Resources Institute Finland (Luke)); Mikołaj Czajkowski (Faculty of Economic Sciences, University of Warsaw)
    Abstract: The paper uses data from a discrete choice experiment to examine information effects on stated preferences for an unfamiliar environmental good, i.e. agricultural genetic resources. We define two groups of respondents based on their use of additional information provided in an internet survey, and model information use and its effect on individual preferences and scale using the logit and mixed logit models. Our findings indicate that both sociodemographic and attitudinal variables affect the use of information, with the respondent’s age, gender, familiarity and perceptions of stakeholder responsibilities having a significant effect. The results show individual preference heterogeneity, but no significant differences in scale between the information groups after allowing the mean coefficients for the attributes to differ. Those who have used the additional information derive higher utility from the changes in the protection of agricultural genetic resources. Our results highlight the importance of genetic resource conservation and controlling for the effects of information use in choice experiment models for unfamiliar goods.
    Keywords: Agricultural genetic resources; Discrete choice experiments; Environmental valuation; Information effects
    JEL: Q51 Q57
    Date: 2019
  2. By: Rahmani, Djamel; Loureiro, Maria; Escobar, Cristina; Gil, Jose Maria
    Abstract: A labelled discrete choice experiment (DCE) combined with a blinded wine tasting was conducted among 180 Catalans red wine drinkers to assess their preferences and willingness to pay (WTP) for three different wines: conventional, organic, and selected vintage organic wines in the context of habitual purchase. The DCE was carried out before and after wine tasting and a comparison between pre and post responses was undertaken to measure the effect of wine taste on wine repurchase. Facial expression analysis was conducted to test whether different wine typologies evoke different emotions and if these emotions influence consumers’ wine choices and WTP. Moreover, we tested for hypothetical bias in the DCE subjecting half of the sample to a hypothetical DCE and the other half to a nonhypothetical DCE. Results show that consumers’ preferences for the three wine typologies in both hypothetical and nonhypothetical DCE were not statistically different. However, consumers’ preferences were significantly influenced by wine taste, evoked emotions and actual liking. Our findings showed that there was a positive and significant association between wine evoked emotions (positive experience) and wine choices, especially in the case of organic and selected vintage organic wine. However, wine evoked emotions did not affect significantly consumers’ WTP for each of the three wine typologies. Our findings also showed that organic or selected vintage organic wines were preferred by women and participants with high environmental involvement. Our findings improved our understanding of wine choices, contributed to the application of DCEs for eliciting preferences and provided useful information to winemakers.
    Keywords: Consumer/Household Economics, Crop Production/Industries
    Date: 2019–04–15
  3. By: Akinwehinmi, Oluwagbenga; Amos, Taiwo; Ogundari, Kolawole
    Keywords: Consumer/Household Economics, Crop Production/Industries, Demand and Price Analysis
    Date: 2019–04–15
  4. By: Kenneth Gillingham; Fedor Iskhakov; Anders Munk-Nielsen; John Rust; Bertel Schjerning
    Abstract: We introduce a computationally tractable dynamic equilibrium model of the automobile market where new and used cars of multiple types (e.g. makes/models) are traded by heterogeneous consumers. Prices and quantities are determined endogenously to equate supply and demand for all car types and vintages, along with the ages at which cars are scrapped. The model allows for transactions costs, taxes, flexible specifications of car characteristics, consumer preferences, and heterogeneity. We apply the model to two examples: a revenue-neutral replacement of the new vehicle registration tax with a higher fuel tax and a hypothetical “merger to monopoly” in an oligopolistic new car market. We show substantial gains in consumer welfare from the tax policy change, as well as important effects on government revenues, automobile prices, driving, fuel consumption and CO2 emissions, while the merger leads to substantial welfare losses.
    Keywords: secondary markets, trade, consumer heterogeneity, transactions costs, dynamic programming, extreme value distribution, dynamic discrete choice, multinomial logit model, stationary equilibrium, Markov chains, invariant distributions
    JEL: D43 D61 H21 H23 L90 Q40 Q58
    Date: 2019
  5. By: Arjan Non; Ingrid Rohde; Andries de Grip; Thomas Dohmen
    Abstract: We conduct a discrete choice experiment to investigate how the mission of high-tech companies affects job attractiveness and induces self-selection of science and engineering graduates with respect to their prosocial attitudes. We characterize mission by whether or not the company combines its profit motive with a mission on innovation or corporate social responsibility (CSR). Furthermore, we vary job design (e.g. autonomy) and contractible job attributes (e.g. job security). We find that companies with a mission on innovation or CSR are considered more attractive. Women and individuals who are more altruistic and less competitive feel particularly attracted to such companies.
    Keywords: Mission of the company, sorting, discrete choice experiment, job characteristics, social preferences disclosure
    JEL: J81 J82 M52
    Date: 2019–06
  6. By: Tait, Peter; Saunders, Caroline; Dalziel, Paul; Rutherford, Paul; Driver, Timothy
    Abstract: Millennials are the largest demographic segment in the USA (Wine Market Council, 2016) and have gained market share of high frequency wine drinkers while Baby Boomers and Gen-X generations are falling in market share (Franson, 2016). This demographic evolution in wine market composition has focused industry attention on expanding understanding of Millennial wine drinkers preferences as an important marketing dynamic. At the same time the wine industry has seen significant establishment of sustainable certification systems as preferences for sustainability have developed and been recognised as an avenue for product diversification in a highly competitive global market. While there is a recognition that preferences for the types of attributes sustainability programmes can deliver may differ between generations, scant research has explored this segmentation. This paper reports on the application of a discrete choice experiment with the objective of comparing generational preferences for individual components of sustainability schemes active in the Californian Sauvignon blanc market. We find consumption behaviour and attribute preference differences over age cohorts. A central finding is that Millennial consumers are willing to pay more for sustainability attributes than both Gen-X and Baby Boomers, while conversely Baby Boomers are willing to pay more for country of origin attributes than both Gen-X or Millennials.
    Keywords: Crop Production/Industries, Production Economics
    Date: 2019–04–15
  7. By: Bensch, Gunther; Peters, Jörg
    Abstract: Free technology distribution can be an effective development policy instrument if market-driven adoption is socially inefficient and hampered by affordability constraints. Yet, policy makers often oppose free distribution, arguing that reference dependence lowers the willingness to pay (WTP) and thus market potentials in the long run. For improved cookstoves, this paper studies the WTP six years after a randomized one-time free distribution in 2009. We demonstrate that the cookstoves were intensely used by the treatment group households in the years after randomization until they reached their designated lifetime. Using a real-purchase offer, we find that both treatment and control households reveal a remarkably high WTP in 2015. The estimated confidence interval suggests that we can exclude a substantial negative effect on the treatment group. The policy implication is that one-time free distribution does not necessarily undermine future market establishment and thus can be an effective policy instrument if rapid dissemination is the objective.
    Keywords: energy access, real-purchase offer, reference dependence, supply chains, technology adoption, willingness to pay
    JEL: D03 D12 O12 O13 Q41
    Date: 2019–03
  8. By: Paul Hindsley; David M. McEvoy; O. Ashton Morgan
    Abstract: Ethically-labeled products – those that address environmental and human-welfare issues – are increasingly prevalent in consumer decision-making. This research estimates the value consumers place on direct trade coffee, a relatively new and complex ethical product. Direct trade coffee is defined by having three attributes that differentiate it from standard coffee: (i) price premiums are paid directly to farmers; (ii) harvesting practices are sustainable; and (iii) the quality of the product is enhanced. The first two attributes of direct trade coffee lead to social benefits while the third is strictly a private benefit. Using a discrete-choice experiment, we find that consumers are willing to pay significant premiums for each of the three attributes, and are willing to pay slightly more for those attributes with social benefits. While we find evidence of heterogeneity in responses, cultural worldviews do not appear to play a significant role in shaping consumers’ values for direct trade coffee. Key Words: ethically-labeled products, impure public goods, direct trade coffee, discrete choice experiments,
    JEL: C72 C91 C92 D02 H41
    Date: 2019
  9. By: Buschmann, Christoph; Röder, Norbert
    Abstract: Growing evidence suggests that biodiversity in the agricultural landscape is declining sharply. Farmland birds are particularly affected, e.g. the lapwing (Vanellus vanellus) population has been decreasing strongly in Germany and Europe. Up to now the European Union has tried to tackle the problem of biodiversity loss mainly with voluntary (second pillar) agri-environmental schemes financed by the European Agricultural Fund for Rural Development (EAFRD). However, only a small fraction of the agricultural land is enrolled in such programs. We analyse different schemes promoting lapwings in order to identify drivers and inhibitors of acceptance. The analysis is based on a discrete choice experiment with 270 arable farmers in Germany. Results show that those scheme attributes associated with EAFRD compliance, the type of sanctioning and a minimum participation period of five years, markedly reduce the farmers’ acceptance. The results have several policy implications. First, it shows clearly that the maximum support rates for agri-environmental and climate measures according to Art. 28 of EU 1305/2013 laid down in Annex 2 are set too low to achieve an effective implementation of the measure. Second, Eco-Schemes which are an element of the European Commission’s legislative proposal for the Common Agricultural Policy (CAP) could be a valid option to address some of the identified caveats. Eco-Schemes that shall be part of the future direct payments will presumably produce higher participation rates since they offer greater flexibility due to the minimum period of only one year and the late timing of the farmers’ decision until mid-May of the running year. In addition, they could provide additional basic income support and not just compensate for the income loss associated with the protection measure.
    Keywords: Agricultural and Food Policy
    Date: 2019–05–29
  10. By: Ben-Othmen, Marie Asma; Ostapchuk, Mariia
    Abstract: Grasslands are a crucial component of the agricultural landscape of most French regions. They contribute to human well-being through the provision of a wide range of ecosystem services such as ruminantfeeding. In this way, they have an impact upon the quality of animal production. Grasslands also support biodiversity conservation by promoting pollination, climate regulation, water quality regulation, landscape quality, etc. Despite these multiple benefits, grassland areas have been rapidly and constantly shrinking over the last 50 years in the face ofthe extension of forage corn considered a more profitable crop. Agri-environmental schemes (AES) have been identified to date as playing a pivotal role in the promotion of a more sustainable and environmentally friendly agricultural practices within the European Union. In this paper, through the application of the Choice Experiment (CE) method, we intend to analyze the factors that influence farmers’ preferences and motivations to join or not an AES involving grasslands restoration in Normandy. We estimate the relative weight of these factors, and we evaluate the willingness to accept changes related to each factor. In addition to the evaluation of the financial contribution, our objective lies in highlighting the role of the collective participation, the technical support and the area of the farm enrolled in the AES. Hence, our study contributes to a better understanding of factors that might alter famers’ behaviour towards new restoration practices. Potential policy implications that emerged from our data are briefly discussed.
    Keywords: Agricultural and Food Policy
    Date: 2019–05–29
  11. By: St\'ephane Bonhomme; Martin Weidner
    Abstract: Economists are often interested in computing averages with respect to a distribution of unobservables. Examples are moments or distributions of individual fixed-effects, average partial effects in discrete choice models, or counterfactual policy simulations based on a structural model. We consider posterior estimators of such effects, where the average is computed conditional on the observation sample. While in various settings it is common to "shrink" individual estimates -- e.g., of teacher value-added or hospital quality -- toward a common mean to reduce estimation noise, a study of the frequentist properties of posterior average estimators is lacking. We establish two robustness properties of posterior estimators under misspecification of the assumed distribution of unobservables: they are optimal in terms of local worst-case bias, and their global bias is no larger than twice the minimum worst-case bias that can be achieved within a large class of estimators. These results provide a theoretical foundation for the use of posterior average estimators. In addition, our theory suggests a simple measure of the information contained in the posterior conditioning. For illustration, we consider two empirical settings: the estimation of the distribution of neighborhood effects in the US, and the estimation of the densities of permanent and transitory components in a model of income dynamics.
    Date: 2019–06
  12. By: Paul Belleflamme; Martin Peitz
    Abstract: We consider two-sided platforms with the feature that some users on one or both sides of the market lack information about the price charged to participants on the other side of the market. With positive cross-group external effects, such lack of price information makes demand less elastic. A monopoly platform does not benefit from opaqueness and optimally reveals price information. By contrast, in a two-sided singlehoming duopoly, platforms benefit from opaqueness and, thus, do not have an incentive to disclose price information. In competitive bottleneck markets, results are more nuanced: if one side is fully informed (for exogenous reasons), platforms may decide to inform users on the other side either fully, partially or not at all, depending on the strength of cross-group external effects and the degree of horizontal differentiation.
    Keywords: price transparency, two-sided markets, competitive bottleneck, platform competition, price information, strategic disclosure
    JEL: D43 L12 L13
    Date: 2019–06

This nep-dcm issue is ©2019 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.