nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2016‒04‒30
fourteen papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. What Do Farmers Want from Crop Insurance Schemes: A Stated Preference Approach By Olila, Dennis; Nyikal, Rose; Otieno, David
  2. A Latent Class Analysis of Public Attitudes Towards Water Resources: Implications for Recreational Demand By Ehrlich, Oren; Bi, Xiang; Borisova, Tatiana; Larkin, Sherry
  3. Turfgrass producer preferences for certification and royalty fee structures By Jayasekera, Deshamithra; Boyer, Tracy; Tong, Benjamin; Martin, Dennis
  4. Willingness to pay for environmental quality and social capital influence in Sweden By George Marbuah
  5. Accounting for unobserved heterogeneity in micro-econometric agricultural production models: a random parameter approach By Koutchade, Philippe; Carpentier, Alain; Femenia, Fabienne
  6. Decomposition of Discrete Choice Model Generated Probabilities and their Robustness to Changing Substantive Knowledge (Conditioning Variables) By Dharmasena, Senarath; Bessler, David A.
  7. Extremists An Experimental Study Of How Social Interactions Change Preferences By Ian Crawford; Donna Harris
  8. Community-Based Management and Interrelations between Multiple Technology Adoption Decisions: Innovations in Village Poultry Farming in Western Africa By Sodjinou, Epiphane; Henningsen, Arne
  9. Does weather matter? How rainfall shocks affect credit risk in agricultural micro-finance By Pelka, Niels; Weber, Ron; Musshoff, Oliver
  10. To Invest or to Sell? The Impacts of Ontario's Greenbelt on Farm Exit and Investment Decisions By Li, Na; Vyn, Richard; McEwan, Ken
  11. Women and Part-Time Farming: Understanding Labor Supply Decisions in Italian Farm Households By Tocco, Barbara; Bailey, Alastair; Davidova, Sophia; Raimondi, Valentina
  12. Farmers' Choice of Cattle Marketing Channels in Rural South Africa: A Transaction Cost Economics Perspective By Ndoro, Jorine; Mudhara, Maxwell; Chimonyo, Michael; Hitayezu, Patrick
  13. Multiple Lenders, Temporary Debt Restructuring, and Firm Performance: Evidence from contract-level data By MIYAKAWA Daisuke; OHASHI Kazuhiko
  14. Who benefits from collective action? Determinants and economic impacts of coffee farmer cooperatives in Ethiopia By Mojo, Dagne; Fischer, Christian; Degefa, Terefe

  1. By: Olila, Dennis; Nyikal, Rose; Otieno, David
    Abstract: Climate change and weather variability are perhaps some of the major challenges facing the world today. In the phase of these challenges, various climate mitigation strategies including financial, production, as well as marketing aspects have played a significant role in cushioning farmers against adverse effects. In Kenya, agricultural insurance is still at a pilot stage after the unsustainable effort in the 1970’s. Despite the noble intention to revive the crop insurance industry, limited empirical information exists on farmers’ preferences for crop insurance. The study employed Choice Experiment (CE) to elicit farmers’ preferences for crop insurance design features among 300 farmers. The analysis employed a random parameter logit (RPL) model. The results show that farmers are willing to pay for various features of crop insurance. These findings are important in informing ex-ante design and improvement of crop insurance programmes in Kenya and the rest of the world.
    Keywords: Crop insurance, Choice experiment, Random parameter logit, Kenya, Crop Production/Industries, Farm Management, C90,
    Date: 2015
  2. By: Ehrlich, Oren; Bi, Xiang; Borisova, Tatiana; Larkin, Sherry
    Abstract: The recent developments of nonmarket valuation have focused on identifying preference heterogeneity and examining the impact it has on consumer’s willingness to pay. The objective of this study is to examine the extent to which heterogeneous environmental attitudes influence demand for freshwater recreational activities as well as the valuation of freshwater recreational benefits. We focus on the St. Johns River, the longest river in Florida, and use a telephone survey of Florida’s residents to elicit information in regards to household outdoor recreational experiences on the river. Information regarding respondent attitudes and perceptions towards Florida’s water resources and natural resource policies was gathered in the survey as well. We employed a latent class analysis to reveal two distinct classes of respondents based on their responses to questions regarding their environmental attitudes and perceptions. We then estimated a recreational demand model with respect to travel costs associated with getting to the river, household income, perceived water quality of the river, and respondents’ environmental attitudes within each latent class. We found that class 1’s individual recreational benefits are twice as large as class 2’s. We contribute to the literature by emphasizing that environmental attitudes directly influence consumer recreational demand and valuation of the river, and should be taken into consideration for water resource management policies.
    Keywords: latent class analysis, travel cost method, recreational demand, freshwater, st. johns river, preference heterogeneity, Consumer/Household Economics, Demand and Price Analysis, Research Methods/ Statistical Methods,
    Date: 2016
  3. By: Jayasekera, Deshamithra; Boyer, Tracy; Tong, Benjamin; Martin, Dennis
    Abstract: Plant scientists have bred turfgrass varieties to create more desirable traits for long-term maintenance, appearance, utility, and resistance to abiotic and biotic stressors. As universities seek to capture revenue to cover research costs, these varieties are increasingly protected by intellectual property rights such as US plant patents and plant variety protection certificates. Producers require license to produce and sell proprietary varieties, and are required to pay royalties, impacting the types of varieties marketed for sale. Therefore, turf breeders must identify producer demand for various grass varieties, and understand their marketability. An online turfgrass preference survey with sod producers using a discrete choice experiment was conducted in Spring 2015. The design incorporated attributes such as variety, certification agency, fee structure, maintenance reduction potential, and price per square foot. Results from the analysis indicate that producers preferred genetically modified breeds and fee structures that allow producers to share the cost with the breed developers.
    Keywords: Consumer Protection, Information and product quality, Consumer/Household Economics, D18, L15,
    Date: 2016
  4. By: George Marbuah (Swedish University of Agricultural Sciences)
    Abstract: The growing recognition of social capital as an important parameter necessary for shaping pro-environmental behaviour and attitudes is well established in the literature and continues to engage the attention of policymakers, academics and citizens in many jurisdictions. In this paper, we contribute to this strand of literature by investigating the extent to which various elements of social capital influences Swedish public’s tendency to contribute financially or through lifestyle changes in order to protect the environment. Using data from the latest wave of the International Social Survey Programme (ISSP) on the environment in 2010, we explore empirically the link between individuals’ willingness to pay (WTP) and social capital influence using an ordered logistic model. The results show, that, individuals in Sweden are fairly willing to pay for the environment and that this decision is principally and significantly influenced by elements of social capital. In particular, we find quite robust results to show that social and institutional trust, environmental group membership among related civic participation activities and adherence to environmental norms significantly impacts the probability of individuals’ decision to sacrifice toward environmental sustainability by paying higher environmental taxes, prices or through standard of living adjustments.
    Keywords: Willingness to pay, Social capital, Environmental protection, Ordered logistic regression, Sweden
    JEL: A13 A14 Q50 Q51
    Date: 2016–04
  5. By: Koutchade, Philippe; Carpentier, Alain; Femenia, Fabienne
    Abstract: To account for the effects of heterogeneity in micro-econometric models has been major concern in labor economics, empirical industrial organization or trade economics for at least two decades. The micro-econometric agricultural production choice models found in the literature largely ignore the impacts of unobserved heterogeneity. This can partly be explained by the dimension of these models which deals with a large set of choices, e.g., acreage choices, input demands and yield supplies. We propose a random parameter framework to account for the unobserved heterogeneity in micro-econometric agricultural production choices models. This approach allows accounting for unobserved farms’ and farmers’ heterogeneity in a fairly flexible way. We estimate a system of yield supply and acreage choice equations with a panel set of French crop growers. Our results show that heterogeneity significantly matters in our empirical application and that ignoring the heterogeneity of farmers’ choice processes can have important impacts on simulation outcomes. Due to the dimension of the estimation problem and the functional form of the considered production choice model, the Simulated Maximum Likelihood approach usually considered in the applied econometrics literature in such context is empirically intractable. We show that specific versions of the Stochastic Expectation-Maximization algorithms proposed in the statistics literature are easily implemented for estimating random parameter agricultural production models.
    Keywords: Heterogeneity, random parameter models, agricultural production choices, Agricultural and Food Policy, Q12, C13, C15,
    Date: 2015
  6. By: Dharmasena, Senarath; Bessler, David A.
    Abstract: Clear understanding of “goodness” and how substantive knowledge contributes to such goodness is generally absent from the economist’s use of probability. Although probability forecast from either subjective experts or from data based on prior theory and models can be generated, it is more problematic to generate a “good probability forecast” with a crisp understanding of what constitutes “good”. Further it is generally not clear to economists how different conditioning information affects this measure of “good.” Heretofore probability forecasts have been evaluated using the Brier Score and its Yates partition. Our work contributes by exploring how different sets of substantive information affect the Brier score and each component of the Yates partition. We will explore partitions associated with a set of observational data on beverages and the associated consumer decision to purchase. Probabilities are modeled using discrete choice models. Results show the higher the substantive knowledge, higher the model’s ability to offer a high probability for events occurred versus low probability for events that did not occur. Also, this model gave rise to lower Brier Score (lower the better) and higher covariance between probabilities offered and events observed. Better sorting of probabilities was demonstrated in the model with more substantive knowledge.
    Keywords: Brier Score, Yates partition, probabilities, discrete choice model, beverages, Consumer/Household Economics, Research Methods/ Statistical Methods, C18,
    Date: 2016–02
  7. By: Ian Crawford; Donna Harris
    Abstract: Abstract: We study the effects of social interactions on individuals’ other-regarding preferences. Using a modified dictator game and a structural choice-revealed preference approach, we compare five models of other regarding preferences and, using our preferred specification, we measure an individual’s preferences before and after subjects have interacted face-to-face in a small group. We then examine whether a change in preferences is observed. We find that these interactions do indeed change individuals’ other-regarding preferences and that these effects are highly heterogeneous. In most groups, preferences of individual group members become more homogenous as might be expected, but we also find that subjects’ preferences can converge towards those of a single key individual in the group whose preferences are both extreme and also unchanging. These key individuals often have strongly egoistic preferences and are also more likely to be male. These effects are more prevalent amongst younger subjects than older.
    Keywords: Other-regarding preferences, social interactions, preference dynamics, preference heterogeneity, social conformity
    JEL: C90 C92 D70
    Date: 2016–03–29
  8. By: Sodjinou, Epiphane; Henningsen, Arne
    Abstract: Community-based management (CBM) of village poultry aims to foster development and reduce poverty in Benin by disseminating five technologies for improving village poultry farming. We develop a theoretical model to analyze multiple technology adoption decisions that takes into account the interrelations between the technologies. Estimates from multivariate probit models indicate significant interrelations between the five adoption decisions. We show how the estimation results, and particularly the different types of marginal effects, can be utilized to deeply analyze the interrelations between adoption decisions. CBM successfully promoted the adoption of various technologies. Some adoption decisions indicate farmers’ general openness towards new technologies.
    Keywords: Community-Based Management, Technology adoption, Multivariate probit, Village poultry, Benin, West Africa, International Development, Research and Development/Tech Change/Emerging Technologies, Q12, Q16, C31, C35, O13, O14,
    Date: 2015
  9. By: Pelka, Niels; Weber, Ron; Musshoff, Oliver
    Abstract: Small-scale farmers in developing countries are undersupplied with capital. Although microfinance institutions have become well established in developing countries, they have not significantly ex-tended their services to farmers. It is generally believed that this is partly due to the riskiness of lending to farmers. This paper combines original data from a Madagascan microfinance institution with weather data to estimate the effect of rainfall on the repayment performance of loans granted to farmers. Results estimated by linear probability models and a sequential logit model show that excessive rain in the harvest period increases the credit risk of loans granted to farmers
    Keywords: Agricultural Finance, Environmental Economics and Policy,
    Date: 2015
  10. By: Li, Na; Vyn, Richard; McEwan, Ken
    Abstract: This paper examines the impact of Ontario’s Greenbelt legislation, a land use policy that permanently protects over 1.8 million acres of land from non-agricultural development, on farmers’ exit and investment decisions. A farm-level panel data set for 32,512 farms in Ontario is used to perform two econometric estimations: a correlated random effects Probit model of farm exit and a dynamic unobserved effects Tobit model of farm investment. The Greenbelt policy is found to have influenced both farm exit and farm investment decisions, with the impact varying depending on location within the Greenbelt. In particular, the results indicate evidence of a negative impact on farm investment, which is contrary to one of the objectives of the Greenbelt policy.
    Keywords: Agricultural Finance,
    Date: 2015
  11. By: Tocco, Barbara; Bailey, Alastair; Davidova, Sophia; Raimondi, Valentina
    Abstract: The pronounced gender gap in Italian agriculture is reflected by lower levels of female labor force participation, labor supply and managerial positions in the farm sector, coupled with their higher incidence of part-time work. The objective of the paper is to investigate the drivers of farm holders’ labor supply decisions while controlling for gender differences. Using micro-data from the Italian agricultural business survey (REA), this study employs a random effects ordered probit over the period 2002-2009. The results highlight significant gender differences in labor market responses. In particular, farm size and livestock systems are found to increase the on-farm labor supply of male farm holders, reflecting the role of men in the farm and gender differences in ownership, control and decision making over productive resources. The diverse impact of farm subsidies on labor supply may suggest the presence of credit constraints in female-operated households, preventing the capitalization of subsidies into fixed assets.
    Keywords: on-farm labor supply, part-time farming, gender-gap in agriculture, Italy., Farm Management, International Development, Q12, J22, J16, J43.,
    Date: 2015
  12. By: Ndoro, Jorine; Mudhara, Maxwell; Chimonyo, Michael; Hitayezu, Patrick
    Abstract: This study empirically tests the hypotheses that information, negotiation, and monitoring costs influence the decision to sell to private buyers, speculators, or at the auction pens among smallholder farmers in KwaZulu-Natal, South Africa. Based on survey data, the results of a Multinomial Logit regression reveal that the probability of selling at the auction vs. selling at farm gate increases during the end-of-year festive season, indicating the scope of market uncertainty surrounding auctions. They also show that the probability of selling at the auction vs. selling to speculators increases with proximity to the auction marketplace and decreases with knowledge of the buyer, suggesting higher opportunity costs of time and efforts associated with selling at the auction, and considerable negotiation and monitoring costs incurred when selling to speculators. Other significant predictors of auction channel selection are volume supplied and farmer’s age. This study concludes with some policy implications.
    Keywords: Livestock Production/Industries, Marketing,
    Date: 2015
  13. By: MIYAKAWA Daisuke; OHASHI Kazuhiko
    Abstract: This paper empirically examines the cause and consequence of private debt restructurings out of court. Using unique contract-level data accounting for Japanese bank loans, we employ probit and multinomial logit estimations to study how demand and approval of debt restructuring are determined, as well as under what conditions one specific form of debt restructuring--temporary debt restructuring--is utilized. The results of our estimations show, first, that the demand of debt restructuring is systematically associated with firm characteristics and the relation-specific characteristics. Second, debt restructurings are more likely to take a "temporary" form when the number of lender banks is larger. Using propensity score matching difference-in-difference estimation, we further find that the performance of firms experiencing temporary debt restructuring significantly deteriorates in comparison with that of firms experiencing non-temporary debt restructuring. Furthermore, such pattern is more likely to be observed when lender banks have weaker balance sheet conditions. These results imply that temporary debt restructuring during our sample period was mainly used as de facto evergreening lending, which ended up deteriorating borrower creditworthiness.
    Date: 2016–03
  14. By: Mojo, Dagne; Fischer, Christian; Degefa, Terefe
    Abstract: Using household survey data gathered from 305 Ethiopian coffee farmers, the determinants and impacts of cooperative membership are explored. A logit model results reveal that the probability of farmers’ membership decision increases with age, education level, family size, and land property. Employing propensity score matching (PSM), no unique membership impact on members’ economic performance and output are found. However, cooperatives have a positive economic benefit to the whole community (members and nonmembers), regardless of membership. The results suggest a need for a mechanism to improve members’ benefits to make cooperatives more meaningful, attractive and sustainable.
    Keywords: Coffee, Cooperative, Ethiopia, impact evaluation, Propensity score matching, Sustainability, Agribusiness, Farm Management, Q12, Q13, Q18,
    Date: 2015

This nep-dcm issue is ©2016 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.