nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2018‒09‒10
sixteen papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. Assessing farmers’ preferences for the future of the Common Agricultural Policy: insights from of a discrete choice experiment in Germany By Latacz, Uwe; Schreiner, Julia
  4. Sovereign Debt Restructuring: A Dynamic Discrete Choice Approach By Maximiliano Dvorkin; Emircan Yurdagul; Horacio Sapriza; Juan Sanchez
  5. YOU CAN DO IT! A MHEALTH INTERVENTION FOR SMOKING CESSATION By Ioana Palade; Cristian Gavriloaia; R?zvan Timi?
  6. Segmentation of Theatre Audiences: A Latent Class Approach for Combined Data By Evgeniy M. Ozhegov; Alina Ozhegova
  7. The Willingness to Pay for Organic Attributes in the UK By Gschwandtner, Adelina; Burton, Michael
  8. Spatial heterogeneity of WTP values for sparsely-located ecosystem services: alternative index approaches applied to agricultural systems By Granado-Díaz, R.; Gómez-Limón, J.A.; Rodríguez-Entrena, M.; Villanueva, A.J.
  9. What ails fishery insurance in China? - Evaluating fishermen's willingness to pay in central coastal areas By Hairong Mu; Hui Zheng; Chunyang Wang
  10. Small Farmers' Preferences for Weather Index Insurance: Insights from Kenya By Sibiko, Kenneth W.; Veettil, Prakashan C.; Qaim, Matin
  11. Improving Drinking Water Quality in South Korea: A Choice Experiment By Gschwandtner, Adelina; Jang, Cheul; McManus, Richard
  12. Examining perceived land tenure security and dispute resolution pathway preferences among landholders: Implications for land governance reforms in Nigeria By Onuorah Hyacinth, Edeh; Mavrotas, George
  13. Inference of Preference Heterogeneity from Choice Data By Annie Liang
  14. Willingness to Accept Incentives for a Shift to Climate – Smart Agriculture among Smallholder Farmers in Southwest and Northcentral Nigeria By Shittu, A.; Kehinde, M.
  15. Identifying the Discount Factor in Dynamic Discrete Choice Models By Jaap H. Abbring; {\O}ystein Daljord
  16. Partial effects estimation for fixed-effects logit panel data models By Francesco Bartolucci; Claudia Pigini

  1. By: Latacz, Uwe; Schreiner, Julia
    Abstract: This paper analyses the determinants of German farmers’ acceptance of alternative agricultural policy packages. The analysis is based on a discrete choice experiment with 434 farmers from across Germany. The study participants presented with the choice of three different policy packages in each of the seven choice sets for which responses were to be given, plus an option to withdraw from the present agricultural policy. The data was analysed using a random parameter logit model and a latent class estimation to reveal preference heterogeneity among those surveyed. Around two thirds of respondents declared themselves to be in favour of the continuation of direct payments. Less than half of the respondents (40 %) were prepared in principle to accept higher standards in the environment and animal welfare in return for continued direct payments. However, nearly one quarter (23%) of those surveyed wanted direct payments to continue without having to do anything in return. The majority of farmers surveyed were against a state safety net through market intervention. One third of respondents wanted the abolition of the Common Agricultural Policy in its present form, including direct payments.
    Keywords: Agricultural and Food Policy, International Development
    Date: 2018–04–18
  2. By: Gillich, Caroline Sophie-Theresia; Lippert, Christian; Krimly, Tatjana
    Abstract: By means of a discrete choice experiment farmers’ preferences for the cultivation of short rotation coppice (SRC) and miscanthus on arable land in selected regions of Baden-Wuerttemberg were investigated. To account for preference heterogeneity data was analyzed using a mixed logit model. Our results show that the cultivation of SRC and miscanthus are valued negatively. Increasing “risk aversion” and “farm size” both increase the implicitly assumed discount rate farmers apply. Nevertheless, derived monetary values suggest relevant potentials to establish SRC and miscanthus.
    Keywords: Production Economics, Resource /Energy Economics and Policy, Risk and Uncertainty
    Date: 2017–08–15
  3. By: Ioana Palade (Babes-Bolyai University)
    Abstract: The topic of this paper approaches a complex issue, namely the migration of medical professionals from rural areas. The Romanian medical system has its lacks, but the real problem is in rural and remote areas, where the working conditions determine the general practitioners? migration. In order to analyze this phenomenon and come up with some solutions, we developed a mixed-method study, having recourse to two research methods: the interview and the Discrete Choice Experiment. The Discrete Choice Experiment will focus on finding out the factors that drive the health professionals to migrate from rural and remote areas. Furthermore, the focus group completes our approach, outlining the health professionals? opinion with regards to the working conditions from rural areas of Bucovina. Also, after analyzing the results, we focus on finding some workforce retention strategies. Our findings suggest that the main factors which determine the migration of physicians are the quality of the facility, housing, length of commitment, study assistance, salary and management. These are the main areas that need improvement. Also, the results of the interviews revealed the fact that the family physicians from rural areas of Bucovina are not satisfied with their working conditions and their salaries.
    Keywords: health professionals, rural areas, migration, retention, workforce
    JEL: I18
    Date: 2018–07
  4. By: Maximiliano Dvorkin (Federal Reserve Bank of St. Louis); Emircan Yurdagul (uc3m); Horacio Sapriza (Federal Reserve Board); Juan Sanchez (Federal Reserve Bank of St. Louis)
    Abstract: Sovereign debt crises generally involve debt restructurings characterized by debt maturity extensions, delayed payments, face-value haircuts, and temporary financial autarky. We develop a novel quantitative model of endogenous sovereign debt maturity choice and restructuring that rationalizes the debt dynamics observed around distressed debt restructurings. The use of dynamic discrete choice solution methods allows us to smooth the borrower's decision rules on default and debt portfolio choices, rendering the problem tractable.
    Date: 2018
  5. By: Ioana Palade (Babes-Bolyai University, College for Advenced Performance Studies); Cristian Gavriloaia (Babes-Bolyai University, College for Advanced Performance Studies); R?zvan Timi? (Babes-Bolyai University, College for Advanced Performance Studies)
    Abstract: This paper intends to approach mHealth interventions and their effectiveness when it comes to smoking cessation. Smoking is a problem not only in Romania, but it?s a worldwide issue. This topic needs to be further studied because applying technology in medical treatments is not a tackled issue in Romania. Our paper aims at analyzing the effectiveness of mHealth interventions on smoking cessation, having recourse to several methods: the focus group and the Discrete Choice Experiment. The Discrete Choice Experiment will focus on finding out the factors that drive the individuals to choose an mHealth intervention in order to quit smoking, despite the traditional types of interventions (medical patches, pills). The focus group completes our approach, outlining how individuals perceive the effectiveness of mHealth interventions for smoking cessation and what a mobile app should contain to be effective when ceasing this behavior. Our findings suggest that individuals tend to turn to a mHealth intervention instead of a traditional one when they can receive rewards or incentives or if they need a quick and accessible solution. What is more, the focus group?s results demonstrate the fact that individuals perceive mHealth interventions as not being effective. Also, mobile interventions should be tailored considering the needs of every individual and should contain a section with medical counseling. Considering these results, we believe that the Romanian medical system must introduce mHealth interventions in order to ease individuals? access to health and have a more patient-oriented system.
    Keywords: mHealth, intervention, mobile app, smoking cessation
    JEL: I19
    Date: 2018–07
  6. By: Evgeniy M. Ozhegov (National Research University Higher School of Economics); Alina Ozhegova (National Research University Higher School of Economics)
    Abstract: Theatrical productions are perishable goods, since the tickets for a particular play cannot be inventoried and sold after the time of the play. In the revenue management of a perishable good, price discrimination is widely used. Since the theatre audience is heterogeneous in terms of visit purpose, ability to perceive quality, willingness-to-pay, the strategy of price discrimination should be developed in the context of theatre segments. In this paper, we segment consumers of the Perm Opera and Ballet Theatre and propose marketing instruments to increase theatre revenue. Since the development of a detailed price discrimination strategy requires data on consumer purchase history, behavioral and socio-demographic characteristics, we combine two data sources: data on ticket purchases and survey data. Using a modication of a latent class logit model for joint revealed and stated preference data we identify four segments of the theater's audience. The study reveals theatregoer segments with dierent willingness-to-pay for performance and seat location characteristics, which allows the development of detailed recommendations on the pricing strategy for various theatre audiences
    Keywords: demand, performing arts, consumer segments, willingness-to-pay.
    JEL: Z11 C53 D12
    Date: 2018
  7. By: Gschwandtner, Adelina; Burton, Michael
    Abstract: There has been almost no recent formal economic analysis of the WTP of British consumers for organic products.1 Given the rising demand for organic products on one hand and the decline in the organically farmed area in the UK on the other hand, this is an important topic to address. The present paper analyses the demand for organic products using both stated and revealed preferences from the same consumers. The stated preference model is based on the respondent’s choice from hypothetical choice sets. Attributes in the stated preference model are based on the ranges of the actual levels of attributes found in shops and are presented to respondents using a fractional factorial statistical design. Three different hypothetical bias treatments are applied in order to reduce hypothetical bias. The stated preference results are validated with the help of actual consumption data from the weekly shopping of the same consumers. The results show that there exists a core of organic consumers of about 20-30% of the sample that have a positive willingness to pay for the organic label. However, consumers seem to be willing to pay more for other attributes such as a higher quality, environmentally friendly production and no chemical usage. Attributes such as animal welfare, and a longer expiry date do not seem to have the same relevance for the UK consumers.
    Keywords: Consumer/Household Economics, Demand and Price Analysis, Marketing
    Date: 2017–04–25
  8. By: Granado-Díaz, R.; Gómez-Limón, J.A.; Rodríguez-Entrena, M.; Villanueva, A.J.
    Abstract: Previous studies demonstrate the existence of spatial heterogeneity in the demand for ecosystem services (ES), especially by showing spatial discounting (namely, distance decay) and the effect of substitute sites. Our study adds to this literature by analyzing diverse ways of modeling these two effects and applying them to a scattered ecosystem which provides various ES. For this purpose, novel spatial approaches using different discounting factors and incorporating the presence of substitutes (density-based vs. area-based indexes) have been tested. The analysis is based on a discrete choice experiment (DCE) focusing on the estimation of willingness to pay (WTP) for the ES provided by olive groves in Andalusia (southern Spain). For the econometric specification, we use random parameter logit models in preference space to assess the performance of the proposed spatial indexes. The results show that the introduction of these spatial indexes significantly improves the fit of the models, with the best outcome found for the area-based index combined with the inverse of the distance. In addition, differences are found depending on the ES. For biodiversity and soil conservation (i.e., predominantly use values), a positive relationship between WTP and the spatial index is found, implying that the larger the nearby olive grove area, the larger individuals’ WTP, while the opposite is found for carbon sequestration (i.e., predominantly non-use value). These results have important implications for the design of public policies aimed at improving the agricultural provision of ES.
    Keywords: Agricultural and Food Policy, Environmental Economics and Policy
    Date: 2018–09–03
  9. By: Hairong Mu (Harper Adams University); Hui Zheng (Ocean University of China); Chunyang Wang (Macau University of Science and Technology)
    Abstract: Despite the remarkable development in its fishery sector, the penetration rate of fishery insurance in China is considerably low. This paper examines the key factors that contribute to the poor performance of fishery insurance in the country and investigates fishermen?s willingness to pay (WTP) for the insurance program, based on a survey of 1,280 fishermen in three coastal cities in China. The results indicate fishermen?s decision on adoption of an insurance scheme depends on various factors, among which the magnitude of loss, insurance awareness and education level all have positive impact, but annual income and years of fishing experience are more likely to have negative effects. In addition, the mean WTP for fishery insurance is estimated to be CNY 579 per family, which is equivalent to 1.5% of fishermen's mean annual income. These results provide several policy implications for not only the government but also researchers and insurance companies.
    Keywords: China, fishery insurance, willingness to pay, double-bounded dichotomous choice contingent valuation method, field survey
    JEL: Q22 H42
    Date: 2018–07
  10. By: Sibiko, Kenneth W.; Veettil, Prakashan C.; Qaim, Matin
    Abstract: Smallholder farmers in developing countries are particularly vulnerable to climate shocks but often lack access to insurance. Weather index insurance (WII) is a promising innovation, but uptake has been lower than expected. WII contracts are not yet sufficiently tailored to the needs and preferences of smallholders. We combine survey and choice-experimental data from Kenya to analyze an existing WII program and how changes in contractual design might encourage uptake. Better training, higher levels of transparency, and offering contracts to small groups rather than individual farmers would increase willingness to pay. Basis risk does not seem to be a major constraint.
    Keywords: Community/Rural/Urban Development, Farm Management, Risk and Uncertainty
    Date: 2017–04–01
  11. By: Gschwandtner, Adelina; Jang, Cheul; McManus, Richard
    Abstract: Increased pollution leads to a constant decrease of drinking water quality worldwide. Due to safety concerns, unpleasant taste and odour only about 3% of the population in South Korea is drinking untreated tap water. The present study uses choice experiments and cost-benefit analysis to investigate the feasibility of installing advanced water treatments in Cheongju waterworks in South Korea. The waterworks is situated in the middle of the country and is providing more than half a million people with drinking water. The study shows that the lower bound of the median WTP for installing a new advanced water treatment system is about $ 2 US/month, which is similar to the average expenditures for bottled water per household in South Korea. Scenarios under which the instalment of the advanced water treatments is feasible are discussed together with environmental solutions in the long-run.
    Keywords: Environmental Economics and Policy, International Development
    Date: 2018–04–16
  12. By: Onuorah Hyacinth, Edeh; Mavrotas, George
    Abstract: Tenure security and efficient dispute resolution mechanism are critical components of land reform initiatives in Nigeria. Yet, there is little understanding of these components, especially their drivers. This study uses ordered and multinomial logit models to examine perceived tenure security and dispute resolution pathway preferences among landholders, respectively. The results indicate variations in the level of perceived tenure security across the various indicators, and different option mix for dispute resolution preferences. Household socio-demographic and plot variables have a significant influence on both perceived tenure security and landholder preferences for dispute resolution pathway.
    Keywords: International Development, Land Economics/Use
    Date: 2018–04–17
  13. By: Annie Liang (Department of Economics, University of Pennsylvania)
    Abstract: Suppose that an analyst observes inconsistent choices from a decision maker. Can the analyst determine whether this inconsistency arises from choice error (imperfect maximization of a single preference) or from preference heterogeneity (deliberate maximization of multiple preferences)? I model choice data as generated from context-dependent preferences, where contexts vary across observations, and the decision maker errs with small probability in each observation. I show that (a) simultaneously minimizing the number of inferred preferences and the number of unexplained observations can exactly recover the correct number of preferences with high probability; (b) simultaneously minimizing the richness of the set of preferences and the number of unexplained observations can exactly recover the choice implications of the decision maker's true preferences with high probability. These results illustrate that selection of simple models, appropriately defined, is a useful approach for recovery of stable features of preference.
    Date: 2016–10–04
  14. By: Shittu, A.; Kehinde, M.
    Abstract: Abstract Shifting to agricultural practices with Climate –smart Agriculture (CSA) potential is crucial in mitigating greenhouse gas emissions. This study applied choice experiment data collected from 548 farm households across two geopolitical zones in Nigeria to assess the preferences for shifting to CSA among smallholders’ farmers using Best Worst Scaling (BWS) technique. Data analysis within ranked –ordered logit regression framework revealed that stronger preference was given to GAPs with manure followed by GAPs without manure and agroforestry across the three models. However, the farmers show strong preference for status quo as against agroforestry in the less restrictive model. Also, farming households’ attribute stronger preference to cultivating agroforestry on freehold and communal lands followed by strong preference for cultivating agroforestry and GAPs with manure on lease and communal land respectively. This shows that tenure type was only important for a shift to agroforestry and GAPs with manure. Willingness to accept (WTA) results suggested that farming households were willing to accept $237/ha & $137/ha to embrace GAPs with and without manure respectively while they were willing to pay $204/ha to avoid shifting to agroforestry in the study area.
    Keywords: Environmental Economics and Policy, Farm Management, International Relations/Trade
    Date: 2018–07
  15. By: Jaap H. Abbring; {\O}ystein Daljord
    Abstract: Empirical applications of dynamic discrete choice models usually either take the discount factor to be known or rely on ad hoc functional form assumptions to identify and estimate it. We give identification results under economically motivated exclusion restrictions on primitive utilities. We show that each such exclusion restriction leads to an easily interpretable moment condition with the discount factor as the only unknown parameter. The identified set of discount factors that solves this condition is finite, but not necessarily a singleton. Consequently, in contrast to common intuition, an exclusion restriction does not provide point identification. In applications, multiple exclusion restrictions are often available. The discount factor can be set estimated from the corresponding moment conditions using existing methods without solving the choice model. Finally, we show that exclusion restrictions have nontrivial empirical content: The implied moment conditions impose restrictions on choices that are absent from the unconstrained model.
    Date: 2018–08
  16. By: Francesco Bartolucci (Dipartimento di Economia Universita' di Perugia); Claudia Pigini (Dipartimento di Scienze Economiche e Sociali - Universita' Politecnica delle Marche)
    Abstract: We develop a multiple-step procedure for the estimation of point and average partial effects in fxed-effects logit panel data models that admit suffcient statistics for the incidental parameters. In these models, estimates of the individual effects are not directly available and have to be recovered by means of an additional step. We also derive a standard error formulation for the average partial effects. We study the finite-sample properties of the proposed estimator by simulation and provide an application based on unionised workers.
    Keywords: Partial effects, Logit model, Quadratic Exponential model, Conditional Maximum Likelihood
    JEL: C12 C23 C25
    Date: 2018–08

This nep-dcm issue is ©2018 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.