nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2015‒11‒07
twelve papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. Patient Preferences for Pain Management Services in Advanced Cancer: Results from a Discrete Choice Experiment By David Meads; John O'Dwyer; Claire Hulme; Phani Chintakayala; Karen Vinall-Collier
  2. Wheat Farmers' Preferences for Wheat Traits in Punjab, Pakistan: A Choice Experiment Approach By Nazli, Hina; Birol, Ekin; Asare-Marfo, Dorene; Tariq, Asjad
  3. Assessing Agricultural Land Use Change in the Midlands Region of KwaZulu-Natal, South Africa: Application of Mixed-Multinomial Logit By Hitayezu, Patrick; Wale, Edilegnaw; Ortmann, Gerald
  4. Signalling Origin: Consumer Willngness to Pay for Dairy Products with the "100% Canadian Milk" Label By Forbes-Brown, Shelicia; Mcheels, Eric; Hobbs, Jill
  5. Contract farming preferences by smallholder rice producers in Africa: a stated choice model using mixed logic By Arouna, Aminou; Adegbola, Patrice; Raphael, Babatunde; Diagne, Aliou
  6. Impact of hedonic evaluation on consumers’ preferences for beef enriched with Omega 3: A Generalized Multinomial Logit Model approach By Baba, Yasmina; Kallas, Zein; Gil, Jose; Realini, Carolina
  7. Are Fair Trade, Carbon Footprint and Organic Attributes competing? Some Evidences from Scotland, Netherland and France By Akaichi, Faical; Grauw, Steven de; Darmon, Paul
  8. Consumer preferences for improved hen housing: Is a cage a cage? By Maurice Doyon; John Cranfield; Stéphane Bergeron; Lota Dabio Tamini; George Criner
  9. Modelling Household Cooking Fuel Choice: a Panel Multinomial Logit Approach By Alem, Yonas; Beyene, Abebe D.; Köhlin, Gunnar; Mekonnen, Alemu
  10. Using Elicitation Mechanisms to Estimate the Demand for Nutritious Maize: Evidence from Experiments in Rural Ghana By Banerji, Abhijit; Chowdhury, Shyamal; Groote, Hugo; Meenakshi, J.V.; Haleegoah, Joyce; Ewool, Manfred
  11. Willingness to Pay for Quality Attributes of Fresh Beef Implications on the Retail Marketing By Berges, Miriam; Casellas, Karina; Rodriguez, Ricardo; Errea, Damian
  12. Relational goods and direct purchase from farmers: estimating the value of the relationship between consumers and producers By Corsi, Alessandro; Novelli, Silvia

  1. By: David Meads (Academic Unit of Health Economics, Leeds Institute of Health Sciences, University of Leeds); John O'Dwyer (Academic Unit of Health Economics, Leeds Institute of Health Sciences, University of Leeds); Claire Hulme (Academic Unit of Health Economics, Leeds Institute of Health Sciences, University of Leeds); Phani Chintakayala (Leeds University Business School & Consumer Data Research Centre, University of Leeds); Karen Vinall-Collier (Academic Unit of Health Economics, Leeds Institute of Health Sciences, University of Leeds)
    Abstract: Pain from advanced cancer remains prevalent, severe and often under-treated. New services are required to improve quality of life for patients with cancer pain. A discrete choice experiment (DCE) was conducted with patients to understand their preferences for pain management services to inform service development. Focus groups were used to develop the DCE ‘attributes’ and ‘levels’. The attributes were waiting time, type of healthcare professional, out-of-pocket costs, side-effect control, quality of communication, quality of information, and pain control. Patients from 13 English palliative care services completed the DCE along with clinical and health-related quality of life (HRQoL) questions. A conditional logit model was used to analyse the data. 221 patients completed the survey (45% female; mean age=64.6, range 21.6-92.2). The most important aspects of services were: good pain control, zero out-of-pocket costs and good side-effect control. Poor/ moderate pain control and £30 costs drew the highest negative preferences. Respondents were willing to incur costs ranging £10.26-£12.51 to reduce waiting time by 2 days, receive good information, good communication or to see a specialist pain doctor. Those with lower HRQoL were less willing to wait for treatment and willing to incur higher costs. Outcomes attributes (good pain control, few side effects) were more important than process attributes (waiting times, type of healthcare professional). However, the preference for good information and communication was greater than that to see some types of healthcare professional. Patients were willing to incur small costs (£10) and wait times to receive their preferred level of service.
    Keywords: discrete choice experiment; cancer pain; patient preferences;
    JEL: J1
    Date: 2015
  2. By: Nazli, Hina; Birol, Ekin; Asare-Marfo, Dorene; Tariq, Asjad
    Abstract: In this paper we implement a stated preference experiment to assess wheat farmers’ preferences for and trade-offs between several wheat attributes, including yield, maturity period, resistance to rust, presence of zinc content, and colour of the roti (flat bread). Since zinc-biofortified wheat varieties were not available at the time this study was implemented, we employed the hypothetical choice experiment method. Choice data are collected from 1116 wheat farmers and analysed using conditional logit models, and accounting for the differences in the preferences of farmers with different size operations (marginal, small-scale and medium and large) located in the three key agro-climatic zones of Punjab. The results of this study are expected aid in the development of zinc-biofortified wheat varieties that are preferred by farmers of different sizes in different agro-climatic zones, as well as in the design of targeted delivery and marketing mechanisms for their maximum adoption.
    Keywords: biofortification, zinc-biofortified wheat, choice experiment, Crop Production/Industries, C35, C93, D12, D83, O33, Q18,
    Date: 2015
  3. By: Hitayezu, Patrick; Wale, Edilegnaw; Ortmann, Gerald
    Abstract: On-farm tree cultivation is considered an important strategy to mitigate detrimental environmental impacts of agricultural land-use change (ALUC). In South Africa, however, little is known about farm-level incentives and constraints that govern ALUC decisions among small-scale farmers. To address this knowledge gap, this study employs a mixed multinomial logit (MMNL) model by using a combination of revealed and stated preference data. After correcting for endogeneity, the estimated results show that decisions about ALUC are rationally derived and driven by clear but heterogeneous preferences and trade-offs between crop productivity, food security and labour saving. The results further show that the decision to plant sugarcane is constrained by landholding, whilst farmland afforestation is negatively influenced by household size. Decisions to convert land use are also driven by the behaviour of peer groups and agro-ecological conditions. Based on these findings, important policy implications for sustainable land use are outlined.
    Keywords: Agribusiness, Land Economics/Use,
    Date: 2015
  4. By: Forbes-Brown, Shelicia; Mcheels, Eric; Hobbs, Jill
    Abstract: In Canada, all fluid milk and cream products must be sourced from Canadian producers under the supply management policy governing the Canadian dairy sector, while other processed dairy products, such as cheese, yogurt, and ice cream can be made using imported milk components. Recently, the Dairy Farmers of Canada launched a 100% Canadian Milk label for products that contain only milk and milk ingredients produced in Canada. This paper uses a Discrete Choice Experiment from a Canada-wide survey of dairy consumers to elicit their willingness-to-pay for ice cream carrying the 100% Canadian Milk label. The results show that Canadian consumers are willing to pay more for ice cream products that carry the label. Consumer knowledge of the dairy sector affects their willingness to pay for this labelling information. Implications for the use of the Canadian origin label and suggestions for further research are discussed.
    Keywords: Willingness to Pay, Ice cream, Stated Preference, Country of Origin, Random Parameters Logit (RPL) model, Consumer/Household Economics, Food Consumption/Nutrition/Food Safety, Q13, Q17,
    Date: 2015
  5. By: Arouna, Aminou; Adegbola, Patrice; Raphael, Babatunde; Diagne, Aliou
    Abstract: In developing countries, smallholder farmers face many constraints including lack of information, access to credit and to markets. To overcome these constraints, resource-poor farmers can engage in contract farming. However, contracts farming need to meet farmers’ demand in order to be sustainable. This study aimed to analyze the preferences of rice farmers for agricultural contracts in Benin. Stated choice data were collected from 579 rice farmers. In order to account for heterogeneity, data were analyzed using mixed logit model. Results showed that producers preferred contracts under the following terms: short term contract (one season), payment at delivery, group selling and having processor as partner. However, the contract preference is different for men and women. The study suggests that this difference and the attribute of preferred contract need to be taking into account for the design of best-fit contract farming by rice value chain actors and policy makers in Sub-Saharan Africa.
    Keywords: Rice, stated preferences, contract farming, mixed logit, Benin, Agricultural and Food Policy, Agricultural Finance, Crop Production/Industries, C5, C90,
    Date: 2015
  6. By: Baba, Yasmina; Kallas, Zein; Gil, Jose; Realini, Carolina
    Abstract: The impact of hedonic evaluation on consumers’ preferences towards beef attributes including its enrichment with polyunsaturated fatty acids (PFA) was evaluated. 647 Spanish consumers were divided into two groups differentiated by the information received. Consumers evaluated five beef attributes (origin, animal diet, amount of visible fat, meat colour and price) by conducting a choice experiment (CE) and using the recently developed Generelized Multinomial Logit (G-MNL). Subsequently, consumers conducted a blind tasting of four different beef samples and later informed about what they taste. Finally consumers repeated the CE. By estimating the G-MNL, it allows respondents to have different utility function scales that describe a different uncertainty levels with respect to the choices they make. In this case, hedonic evaluation of beef samples and information had a significant impact on consumer beef preferences, choices and scale parameters. Results show that giving consumers additional information, the average error scales decreased significantly.
    Keywords: Consumer preferences, beef, Choice Experiments, Generalized multinomial logit., Food Consumption/Nutrition/Food Safety, Livestock Production/Industries, C5, C90, Q13,
    Date: 2015
  7. By: Akaichi, Faical; Grauw, Steven de; Darmon, Paul
    Abstract: A choice experiment was conducted in Scotland, the Netherlands and France to assess consumers’ preferences and willingness to pay (WTP) for ethical attributes (i.e. fairtrade, organic, lower carbon footprint) of bananas and to find out whether this ethical food attributes are competing in real markets. The results showed that in the three countries consumers are willing to pay a price premium for the three ethical food attributes. The results showed that in the current market situation these ethical foods are not generally competing against each other. Nonetheless, they are likely to become competing for consumer’s money at least when: (1) the price of organic foods is decreased significantly, (2) the price for fairtrade food products is set higher than consumers’ WTP, and (3) bananas labelled has having lower carbon footprint are made available in retail stores and sold at a price lower than consumers’ WTP.
    Keywords: Fairtrade, organic, carbon footprint, willingness to pay, competition, choice experiment. JL, Environmental Economics and Policy, D12, Q13,
    Date: 2015
  8. By: Maurice Doyon; John Cranfield; Stéphane Bergeron; Lota Dabio Tamini; George Criner
    Abstract: There is growing concern amongst some consumers regarding animal welfare in livestock production. Several regions, including California and the European Union, have banned the use of battery cage production systems for laying hens. In Quebec, battery cages are being phased out with new barns required to be equipped with enriched cages. In this paper, the empirical data from two discrete choice experiments (DCE) are used to understand Quebec consumers’ demand for alternative laying hen housing systems and desired attributes. The results of the first DCE suggest that Quebec consumers are not willing to pay a premium for eggs produced in enriched cage systems, in spite of evidence that they prefer aspects of that system. Using an online survey we find that consumers have a negative stigma related to the word ‘cage’. A second DCE is therefore conducted to estimate consumer preferences for different amenities commonly found in enriched cage systems, without the possible negative framing effect from the word “cage”. The results suggest that consumers have a positive value for the enhanced housing system for laying hens, results also indicate a differentiated demand for the various elements of the enhanced system. Les consommateurs sont de plus en plus soucieux du bien-être animal. Plusieurs régions, incluant la Californie et l’Europe, interdissent l’élevage de poules dans des systèmes de cages traditionnelles. Au Québec, ce type de cage sera graduellement éliminé, les producteurs ayant collectivement décidé que les nouvelles constructions seront équipées de cages enrichies. Ce papier présence les résultats de deux enquêtes avec choix expérimentaux discrets (CED) qui permettent de mieux comprendre la demande des consommateurs québécois pour les différents éléments d’un système de cage enrichie. La première enquête démontre une absence de valeur positive pour ce système, bien que les éléments du système de cage enrichie soient valorisés. Une enquête en ligne démontre un fort biais négatif associé au mot cage. Un deuxième CED, qui n’utilise pas le mot cage, est utilisé pour déterminer les préférences des consommateurs pour les différents éléments d’un système de cage enrichie. Les résultats indiquent une valeur positive pour le système enrichie avec des valeurs différenciées selon les éléments qui composent ce système de logement des pondeuses.
    Keywords: , eggs, choice experiment, framing, enhanced cage, furnished cage
    Date: 2015–10–23
  9. By: Alem, Yonas (Department of Economics, School of Business, Economics and Law, Göteborg University); Beyene, Abebe D. (Environmental Economics Policy Forum, EDRI, Ethiopia); Köhlin, Gunnar (Department of Economics, School of Business, Economics and Law, Göteborg University); Mekonnen, Alemu (Department of Economics, Addis Ababa University, Ethiopia)
    Abstract: We use three rounds of a rich panel data set to investigate the determinants of household cooking fuel choice and energy transition in urban Ethiopia. We observe that the expected energy transition did not occur following economic growth in Ethiopia during the decade 2000-2009. Regression results from a random effects emultinomial logit model suggest that households’economic status, price of alternative energy sources, and education are important determinants of fuel choice in urban Ethiopia. The results also suggest the use of multiple fuels, or “fuel stacking behavior” by households. We argue that policy makers could target these policy levers to encourage transition to cleaner energy sources.
    Keywords: Ethiopia; urban; energy choice; random effects multinomial logit
    JEL: C25 O13 Q23 Q42
    Date: 2015–10
  10. By: Banerji, Abhijit; Chowdhury, Shyamal; Groote, Hugo; Meenakshi, J.V.; Haleegoah, Joyce; Ewool, Manfred
    Abstract: We conduct a field experiment in Ghana to assess (a) consumers’ willingness to pay (WTP) for a provitamin A maize variety, (b) the performance of three elicitation mechanisms (Becker-DeGroot-Marschak [BDM] mechanism, kth price auction, and choice experiment) in eliciting WTP, (c) the effect of participation fees on WTP and (d) the effect of nutrition information on WTP. WTP results are similar in magnitude across the three elicitation mechanisms. Variation in participation fee has no effect on estimated WTP in the two mechanisms that varied participation fee, suggesting that people did not have a higher propensity to spend out of windfall income. In the absence of information on the nutrient density of the provitamin A maize variety, consumers are willing to pay less for it than the existing varieties; however, nutrition information transforms this discount into a substantial premium.
    Keywords: biofortification, provitamin A maize, Becker-DeGroot-Marschak mechanism, kth price auction, choice experiment, participation fee, Crop Production/Industries, Food Consumption/Nutrition/Food Safety, C35, C93, D12, D83, Q18,
    Date: 2015
  11. By: Berges, Miriam; Casellas, Karina; Rodriguez, Ricardo; Errea, Damian
    Abstract: In recent decades, the demand for food worldwise has undergone significant changes that have highlighted the issue of the quality and safety of food consumed. After international food crisis associated with consumption of fresh meat, consumer concerns about the quality and safety of these products has been increased. However, the atrribtures for assessing the safety of fresh meat consumption are not firectly observable; they are credence attributes. The aim of this work is to investigate consumers' preceptions of safety in Argentina and identify factors that help expalin consumers' willingness to pay for different attributes related safety of the beef products, including, a hypothetical hygiene certification in handling and retailing. The results indicate a positive willingness to pay for fresh meat atrributes such as personalized attention in a butcher counter, the presense of a "safety certification" in the place of purchase and the bright red color on the product.
    Keywords: Agricultural Finance, Food Consumption/Nutrition/Food Safety, Marketing,
    Date: 2015
  12. By: Corsi, Alessandro; Novelli, Silvia
    Abstract: Personal relationships can affect economic life and they may be even more important in Alternative Food Networks. We estimate the value of the relational good produced by the personal relationship in direct sales by farmers. This is relevant for assessing the importance of personal interaction in a typically economic behavior like food purchase. Drawing from theoretical considerations, we employ a stated preferences methodology to estimate the value consumers buying directly from farmers attach to their particular choice of vendor. We estimated a difference-in-utility model and a model based on the valuation function, using data from a consumer survey in open-air markets in four towns in Piedmont Region (Italy). Contingent on the chosen model, the average value is 10-12 percent of the consumers’ expenditure for fruits and vegetables, and up to 1.2-1.3 percent of their overall income.
    Keywords: relational goods, stated preferences, direct sales, alternative food networks, Agricultural Finance, Consumer/Household Economics, C5, D1, Q13,
    Date: 2015

This nep-dcm issue is ©2015 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.