nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2013‒06‒24
nineteen papers chosen by
Edoardo Marcucci
Universita' di Roma Tre

  1. Consequential Cash Choice Experiments: Provision Rules and Decision Support for Restoration of NROCs Ecosystem By Kafle, Achyut; Swallow, Stephen K.
  2. The use of Stated Preferences to forecast alternative fuel vehicles market diffusion: Comparisons with other methods and proposal for a Synthetic Utility Function By Jérôme Massiani
  3. PPML estimation of dynamic discrete choice models with aggregate shocks By Artuc, Erhan
  4. Public Acceptance of and Willingness to Pay for Nanofood: Case of Canola Oil By Zhou, Guzhen; Hu, Wuyang; Schieffer, Jack; Robbins, Lynn
  5. Consumer Preference for Eggs from Enhanced Animal Welfare Production System: A Stated Choice Analysis By Lu, Yiqing; Craneld, John
  6. Using a Control Function to Resolve the Travel Cost Endogeneity Problem in Recreation Demand Models By Melstrom, Richard T.; Lupi, Frank
  7. An Examination of Consumer Willingness to Pay for Local Products By Adalja, Aaron; Hanson, James; Towe, Charles; Tselepidakis, Elina
  8. Will Reducing the Calorie Content of School Lunches Affect Participation? Evidence from a Choice Experiment with Suburban Parents By Pham, Matthew V.; Roe, Brian E.
  9. Stripping Because You Want to Versus Stripping Because the Money is Good: A Latent Class Analysis of Farmer Preferences Regarding Filter Strip Programs By Howard, Gregory; Roe, Brian E
  10. Anonymous Social Networks versus Peer Networks in Restaurant Choice By Tiwari, Ashutosh; Richards, Timothy J.
  11. The Effects of Intertemporal Considerations on Consumer Preferences for Biofuels By Khachatryan, Hayk; Joireman, Jeff; Casavant, Ken
  12. Individualized or non-individualized IDM: What elicits consumer preferences best? By Langena, Nina; Klink, Jeanette; Hartmann, Monika
  13. Chinese Producer Behavior: Aquaculture Farmers in Southern China By Ortega, David; Wang, H. Holly; Widmar, Nicole J. Olynk; Wu, Laping
  14. The Chicken Wears No Skin: Ordering Eects in Elicitation of Willingness to Pay for Multiple Credence Attributes in Ethical and Novel Food Products By Cash, Sean B.; Slade, Peter; Craneld, John
  15. Market Supply Analysis: Landowner Preferences for Ecosystem Service Provision in Wyoming By Duke, Esther; Hansen, Kristiana; Bond, Craig
  16. Farmers’ preferences and social capital towards agri-environmental schemes for protecting birds By Alló, Maria; Igleasias, Eva; Loureiro, Maria L.
  17. How much of the error term is explained by psychometric variables? The example of organic produce demand By Grebitus, Carola; Dumortier, Jerome
  18. Market Intermediaries' Willingness to Pay for Rosaceous Tree Fruit Attributes By Li, Huixin; Gallardo, R. Karina; McCracken, Vicki; Yue, Chengyan; Luby, James; McFerson, James R.
  19. Cash versus In-Kind: Farmer Valuation of Seed Traits and Differences in Willingness-to-Pay By Hossack, Fiona; An, Henry

  1. By: Kafle, Achyut; Swallow, Stephen K.
    Abstract: Investigating incentives, through valuation context and questions, that motivate respondents to reveal their true values for environmental good under consideration has been a long-standing area of research in stated preference literature. A large number of previous non-market valuation studies have focused on various dimensions of valuation questions and context and have investigated how these dimensions a↵ect the incentives to answer truthfully. An importnat, but relatively less-explored, area is the incusion of a provision rule, by which environmental good under investigation will be provided, and how this a↵ects participants’ incentives to tell the true values. Provision rules, that are made explicit to survey respondents, provide a connection between survey choices and actual outcomes. Advancements in Mechanism Design Theory have recently attracted researchers’ attention on examining alternative provision rules using discrete choice experiments (DCE) and comparing preferences and tradeo↵s across provision rules. Only very few studies,mostly in laboratory experiments, have attempted to examine the influence of the inclusion of a provision rule in elicited preferences and tradeo↵s. Employing a split-sample approach, this study compares a single decision-maker’s choice and a plurality vote provision rules in in-person choice experiments using real cash for actual implementation of ecosystem restoration project on the ground. A very preliminary conditional logit model results suggest that both rules produce statistically similar preference functions in terms of marginal values and tradeo↵s between restoration attributes. Further analysis is yet to be conducted to ensure these preliminary results hold consistently using a Latent Class Model to incorporate preference heterogeneity for ecosystem restoration.
    Keywords: provision rules, real-money choice experiments, ecosystem restoration, decision-support tool, Demand and Price Analysis, Research Methods/ Statistical Methods,
    Date: 2013
  2. By: Jérôme Massiani (Department of Economics, University of Venice Cà Foscari)
    Abstract: Stated Preferences are, together with Bass diffusion and, to a lesser extent, Total Cost of Ownership, the most popular methods to forecast the future diffusion of electric and alternative fuel vehicles. In this contribution, we compare the merits and limitations of SP relative to other methods. We also review the empirical results provided by SP surveys and assess their validity for modeling market diffusion. We also propose a meta-analysis-based Synthetic Utility Function that consolidates results across various studies and can be used, for simulation purpose, in a Discrete Choice Model context. Such an approach makes the simulation results less dependent of single surveys’ idiosyncrasies, and hence is helpful for the formulation of robust policy recommendations.
    Keywords: Stated Preferences, Alternative fuel vehicle, market diffusion
    JEL: C53 O33
    Date: 2013
  3. By: Artuc, Erhan
    Abstract: This paper introduces a computationally efficient method for estimating structural parameters of dynamic discrete choice models with large choice sets. The method is based on Poisson pseudo maximum likelihood (PPML) regression, which is widely used in the international trade and migration literature to estimate the gravity equation. Unlike most of the existing methods in the literature, it does not require strong parametric assumptions on agents'expectations, thus it can accommodate macroeconomic and policy shocks. The regression requires count data as opposed to choice probabilities; therefore it can handle sparse decision transition matrices caused by small sample sizes. As an example application, the paper estimates sectoral worker mobility in the United States.
    Keywords: Economic Theory&Research,Science Education,Scientific Research&Science Parks,Statistical&Mathematical Sciences,Econometrics
    Date: 2013–06–01
  4. By: Zhou, Guzhen; Hu, Wuyang; Schieffer, Jack; Robbins, Lynn
    Abstract: Nanotechnology has tremendous potential in food and agriculture. Few economic studies focused on specific products made using nanotechnology, let alone food or food related products. Using a national choice experiment survey, this analysis examines consumers’ valuations for nano-attributes. As implied, consumers were willing to pay less for canola oil if it was produced from nanoscale-modified seed; less if the final products were packed with nanotechnology-enhanced packaging technique; and no significant difference was found for oil that was designed with health enhancing nano-engineered oil drops, which would require interaction with the human digestive system. Additionally, the results revealed unobserved heterogeneities among respondents in their willingness-to-pay for canola oil attributes. Findings from this study will help bridge the gap between scientific innovation and public policy and social-economic concerns. Implications for government policy that can be efficiently used to monitor and regulate these technologies were also investigated.
    Keywords: Choice experiment, Mixed Logit model, Nanotechnology application, Willingness to Pay, Agribusiness, Agricultural and Food Policy, Consumer/Household Economics, Food Consumption/Nutrition/Food Safety, Marketing, Research Methods/ Statistical Methods, Q13, Q16,
    Date: 2013–08–04
  5. By: Lu, Yiqing; Craneld, John
    Abstract: The rst choice experiment investigated consumer preferences for dierent housing systems, while the second investigated consumer preferences for attributes of a housing system. Each choice experiment had two information treatments. In both treatments, a description of each housing system was provided, while in the second treatment, there was additional information regarding the consequences (in terms of eect on birds) of each housing systems based on scientic research. The results indicate that Canadian consumers are willing to pay a premium for eggs from free run and free range systems, but not for eggs from enriched cage systems. There are also positive marginal WTPs for cage-free, outdoor access, access to nests box, perches, scratching pads and more space. In both choice experiment, the WTP for enhanced animal welfare attributes are lower in treatment 2 (with additional information) than treatment 1. Consumer preference for outdoor access is quite consistent across two choice experiments.
    Keywords: Consumer/Household Economics, Livestock Production/Industries, Public Economics,
    Date: 2013
  6. By: Melstrom, Richard T.; Lupi, Frank
    Abstract: This paper proposes using a control function to correct for endogeneity in recreation demand models. The control function approach is contrasted with the method of alternative specific constants (ASCs), which has been promoted in prior research. As an application, we consider the case of travel cost endogeneity in the demand for Great Lakes recreational fishing. Using data on Michigan anglers, we employ a random utility model of site choice. We show that either ASCs or the control function will correct for travel cost endogeneity, although we find that the model with ASCs produces significantly weaker results. Overall, compared with traditional approaches control functions may offer a more flexible means to eliminate endogeneity in recreation demand models.
    Keywords: Recreation demand, random utility model, travel cost method, travel cost endogeneity, control function, alternative specific constants, recreational fishing, Environmental Economics and Policy, Research Methods/ Statistical Methods,
    Date: 2013
  7. By: Adalja, Aaron; Hanson, James; Towe, Charles; Tselepidakis, Elina
    Abstract: This paper uses stated and revealed preference data from a choice-based conjoint survey instrument to estimate willingness to pay for distance-based local food products. The survey was administered to three different groups of respondents: members of a consumer buying club, a random sample of Maryland residents, and suburban Maryland grocery store shoppers. We find that both the random sample of Maryland residents and the grocery store shoppers are willing to pay a premium for local products, but view locality and production method as substitutes. Conversely, more selective shoppers, members of a consumer buying club, are willing to pay less for local than their counterparts, but do not conflate local with other premium attributes, such as grass-fed production.
    Keywords: conjoint analysis, field experiment, local, grass-fed, willingness to pay, beef, Livestock Production/Industries, Production Economics,
    Date: 2013–06–03
  8. By: Pham, Matthew V.; Roe, Brian E.
    Keywords: Choice Experiment, Calorie, National School Lunch Program, NSLP, Food Consumption/Nutrition/Food Safety, Health Economics and Policy, Institutional and Behavioral Economics,
    Date: 2013
  9. By: Howard, Gregory; Roe, Brian E
    Abstract: Governments in Ohio have attempted to limit nutrient runoff in the Maumee watershed from agriculture through the establishment of Payment for Ecosystem Services (PES) programs, in which farmers are paid to implement Best Management Practices (BMPs) such as grass filter strips. This paper seeks to understand which farmers are likely to opt into these PES programs and how farmer preferences for these programs are influenced by program attributes and farmer perceptions towards BMPs. We examine these questions using responses from a survey of Ohio farmers, where farmers choose between two PES programs and a status quo (no program) option. We allow for farmer heterogeneity using latent class analysis and find two classes of farmers. One class, denoted the “Environmental Steward” class, has a strong preference for opting into filter strip programs. Furthermore, increasing perceptions of filter strip effectiveness has no significant impact on program choice for this class. The second class, denoted the “Other” class, has a strong status quo preference. Increasing perceptions of filter strip effectiveness has a significant positive effect on members of this class. Both classes prefer programs with larger payments, smaller filter strips, and less paperwork, while program length is not significant.
    Keywords: Agricultural and Food Policy, Environmental Economics and Policy,
    Date: 2013
  10. By: Tiwari, Ashutosh; Richards, Timothy J.
    Abstract: We compare the effect of anonymous social network ratings ( and peer group recommendations on restaurant demand. We conduct a two stage choice experiment and combine it with online social network reviews from and find that peers have a stronger impact on restaurant demand than anonymous reviewers.
    Keywords: Peer Networks, Anonymous Networks, Economic Experiment, Social Dining, Community/Rural/Urban Development, Consumer/Household Economics, Food Consumption/Nutrition/Food Safety, Institutional and Behavioral Economics,
    Date: 2013–05–31
  11. By: Khachatryan, Hayk; Joireman, Jeff; Casavant, Ken
    Abstract: The relationship between the consideration of future and immediate consequences (CFC) and consumer preference for gasoline, cellulose-based and corn-based ethanol fuels was investigated using data from a representative panel of U.S. consumers. A panel of U.S. consumers completed the consideration of future consequences-14 scale, and made a series of choices in fueling scenarios. Results showed that the CFC score was positively associated with the choice for alternative transportation fuels. As the CFC score increases from its minimum to maximum, the predicted probability of choosing cellulose- and corn-based ethanol fuels increases from 14% to 61%, and 22% to 30%, respectively, and the probability of choosing gasoline drops from 64% to below 10%. Additional analyses showed that the CFC-Future and CFC-Immediate subscales were unique predictors of preference for biofuels. Implications for marketing of biofuels are discussed.
    Keywords: consideration of future and immediate consequences, choice of biofuels, environmental behavior, discrete choice model, Consumer/Household Economics, Institutional and Behavioral Economics, Resource /Energy Economics and Policy,
    Date: 2013
  12. By: Langena, Nina; Klink, Jeanette; Hartmann, Monika
    Abstract: In this paper we measure consumers’ preferences for different (ethical) product attributes by questionnaires and compare the results to the ones obtained using an individualized and a nonindividualized Information Display Matrix (IDM). The latter contains only those attributes the respective respondent stated to be important for her purchase decision. The products considered in our study are ham and coffee. The findings first confirm that the IDM is able to reduce social desirability effects, a problem which likely is of relevance in surveys investigating the relevance of ethical product characteristics. Second, using sequence analysis we show that the intensity of the information search process is significantly higher in the case of an individualized IDM compared to a standardized one. In fact in the latter many consumers neglect half of the attributes presented. Thus, using a standardized IDM implies the risk that product characteristics important for consumers’ purchase decision are left out while others that are of little or no relevance are included. Third, we show that it is possible and can be considered as a methodological advancement in IDM research to apply sequence analysis to data acquired via an IDM. Different indicators allow quantifying main characteristics of consumers’ information search process and make it possible to test for significant differences between data obtained from different IDM experiments.
    Keywords: Consumer/Household Economics, Food Consumption/Nutrition/Food Safety, Research and Development/Tech Change/Emerging Technologies,
    Date: 2013
  13. By: Ortega, David; Wang, H. Holly; Widmar, Nicole J. Olynk; Wu, Laping
    Abstract: The increasing share of imported food in developed countries, such as the US and European Union countries, poses new challenges for food safety and quality regulators. China as the world’s biggest food producer has the fastest growing share of fish and shellfish exports to these countries. While there have been an increasing number of studies conducted on consumer demand for various food product attributes, little research has been focused on producer behavior, and studies on Chinese food producers are especially absent in the literature. The objective of this study is to assess Chinese aquaculture producers’ willingness-to-change (WTC) and adopt certain production practices related to food safety. Producer preferences for enhanced food safety measures, and sustainable/eco-friendly production practices are assessed using a choice experiment. Primary data was collected in the leading aquaculture producing provinces of southern China. The average net income per farmer of our sample was 81,286 RMB/year of which approximately 72% originated from their aquaculture operation. Derived WTC estimates from a random parameters logit model suggest that the representative Chinese producer would require a 2.49 % premium per jin of fish to adopt enhanced food safety practices such as those required for China GAP, and No Public Harm voluntary certifications and they would accept a 3.22% discount before being indifferent between having an antibiotic-free facility and using antibiotics. WTC estimates of sustainable eco-friendly practices and verification by various entities were also assessed. A latent class model (LCM) is used to segregate producers into group with similar underlying characteristics to develop policies to improve producer practices and ultimately product safety and quality.
    Keywords: Agricultural and Food Policy, Farm Management, Institutional and Behavioral Economics, International Relations/Trade,
    Date: 2013
  14. By: Cash, Sean B.; Slade, Peter; Craneld, John
    Abstract: We investigate whether consumer preferences for food products embodying multiple cre- dence attributes are easily satiated. Results from two treatments of an experiment suggest choices are not aected by the order in which attributes are presented. Initial evidence suggests diminishing marginal utility in the number of attributes included in food products embodying multiple credence attributes. However, further testing reveals that preferences are consistent with constant marginal utility in the number of product attributes, suggesting that preferences are not easily satiated.
    Keywords: Consumer/Household Economics, Food Consumption/Nutrition/Food Safety, Livestock Production/Industries,
    Date: 2013
  15. By: Duke, Esther; Hansen, Kristiana; Bond, Craig
    Abstract: Our team is establishing a Payment for Ecosystem Services (PES) market, whereby landowners (primarily engaged in cattle and hay production) implement best management practices that result in provision of ecosystem services (wildlife habitat and water resources/ riparian function), in exchange for payment from voluntary buyers (for example, energy companies in need of off-site mitigation credits). The PES market is called the Upper Green River Conservation Exchange and is currently conducting pilot transactions. How do we structure the market to ensure voluntary landowner (i.e., seller) participation? Issues include how to deal with grazing allotments on public lands, how to structure the risk of non-attainment of ecological target outcomes; and which ecosystem services/management practices and contract terms are of interest on a working landscape in this region. We present the results of a survey designed to inform analyses of factors affecting landowners’ stated willingness to participate in a PES market; and program design preferences: what ecosystem services (wildlife habitat and water resources/riparian function) and program features (management practice, contract length, payment level) are of interest to landowners (choice experiment analysis).
    Keywords: payment for Ecosystem Services, environmental markets, choice experiment, landowner survey, Environmental Economics and Policy,
    Date: 2013
  16. By: Alló, Maria; Igleasias, Eva; Loureiro, Maria L.
    Abstract: The steady decline of birds living in steppes is a worrying situation that the European Commission is attempting to remediate through the application of agri-environmental schemes (AES). The aim of this study is to assess farmers’ preferences towards these AES, which call for a number of harvesting restrictions in order to protect birds. We conducted a face-to-face survey in farming communities in Aragon (Spain) and through the estimation of a Rank Ordered Logit model, we found that farmers have strong preferences in favor of these AES. They generally request relative small amounts of monetary compensations to comply with the contractual requirements established by the proposed AES. Our results also show the importance of social trust and expectation of compliance by other neighbors that encourage farmers to cooperate with AES. These and other results may be used to design more effective AES and remediate this important biodiversity problem.
    Keywords: agri-environmental schemes, birds, farmers’ preferences, rank ordered logit, social capital, Environmental Economics and Policy, International Relations/Trade,
    Date: 2013
  17. By: Grebitus, Carola; Dumortier, Jerome
    Abstract: This paper analyzes the impact of human values and personality on the demand for organic tomatoes applying open-ended choice experiments to data from an online study that was performed in summer 2012. Results show that consumers make a distinction between conventional and organic produce, such that human values have a differential impact with regard to predicting demand for products associated with organic labels. Also, consumers distinguish between conventional and organic produce, such that personality has a differential impact with regard to predicting demand for products associated with organic labels. However, results are not as strong as for human values. Overall, results indicate that human values and personality are able to explain a portion of the variability of demand for organic tomatoes.
    Keywords: demand, human values, open ended choice experiments, organic, personality, tobit model, Consumer/Household Economics, Crop Production/Industries, Demand and Price Analysis, M31, Q13,
    Date: 2013
  18. By: Li, Huixin; Gallardo, R. Karina; McCracken, Vicki; Yue, Chengyan; Luby, James; McFerson, James R.
    Keywords: Consumer/Household Economics, Crop Production/Industries,
    Date: 2013
  19. By: Hossack, Fiona; An, Henry
    Keywords: Consumer/Household Economics, Research Methods/ Statistical Methods,
    Date: 2013

This nep-dcm issue is ©2013 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.