nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2014‒04‒18
twelve papers chosen by
Edoardo Marcucci
Universita' di Roma Tre

  1. Discrete Choice Decision-Making with Multiple Decision Makers within the Household By André De Palma; Nathalie Picard; Ignacio Inoa
  2. Valuation of Small and Multiple Health Risks: A Critical Analysis of SP Data Applied to Food and Water Safety By Henrik Andersson; Arne Risa Hole; Mikael Svensson
  3. Estimation of Labour Supply in New Zealand By Joseph Mercante; Penny Mok
  4. Are Ghettos Good or Bad? Evidence from U.S. Internal Migration By Zhang, Junfu; Zheng, Liang
  5. Consumers’ valuation of national versus foreign varieties of tomatoes: results of a contingent valuation study in Portugal By Anabela Botelho; Isabel Dinis; Lina Sofia Lourenço-Gomes; Jorge Moreira; Lígia M.Costa Pinto
  6. The Illiquidity of Water Markets By Donna, Javier; Espin-Sanchez, Jose
  7. Are bad health and pain making us grumpy? An empirical evaluation of reporting heterogeneity in rating health system responsiveness By G. Fiorentini; G. Ragazzi; S. Robone
  8. La responsiveness dei sistemi sanitari: un’analisi empirica sull’assistenza ospedaliera nel Servizio Sanitario Regionale dell’Emilia Romagna By S. Robone; G. Fiorentini; M. A. Nicoli; S. Rodella
  9. Doing R&D in a Closed or Open Mode: Dynamics and Impacts on Productivity By Julio Rosa; Pierre Mohnen
  10. Do Happier Britons Have More Income? First-Order Stochastic Dominance Relations By Hammond, Peter J; Liberini, Federica; Proto, Eugenio
  11. Female Labour Force Participation in MENA’s Manufacturing Sector: The Implications of Firm-related and National Factors By Ali Fakih; Pascal L. Ghazalian
  12. Health Status, Disability and Retirement Incentives in Belgium By Alain Jousten; Mathieu Lefebvre; Sergio Perelman

  1. By: André De Palma (Department of Economics, Ecole Polytechnique - CNRS : UMR7176 - Polytechnique - X, ENS Cachan - École Normale Supérieure de Cachan - École normale supérieure [ENS] - Cachan); Nathalie Picard (Department of Economics, Ecole Polytechnique - CNRS : UMR7176 - Polytechnique - X, THEMA - Théorie économique, modélisation et applications - CNRS : UMR8184 - Université de Cergy Pontoise); Ignacio Inoa (THEMA - Théorie économique, modélisation et applications - CNRS : UMR8184 - Université de Cergy Pontoise)
    Abstract: There is still a long way to achieve the goal of providing a theoretical and empirical framework to model and apply economics of the family. Decision-making within the family has been neglected too long in transportation. Two special issues by Bhat and Pendyala, 2005 [17] and by Timmermans and Junyi Zhang, 2009 [81] provide the most notable exceptions. The objective of this paper is to set-up a flexible framework to discuss the development of integrated transportation models involving interacting and interdependent actors; updating previous reviews from the point of view of economics of the family . Transportation is very keen to have access to this type of models, since their applications are numerous. Let mention, for example, residential location choice, workplace choice, car ownership, choice of children's school, mode choice, departure time choice activity patterns and the like. The (non unitary) economics of the family models are totally different models, which do not merely extend existing discrete choice models. They introduce new concepts, which are specific to within family interactions: negotiation, altruism, or repeated interaction and Pareto optimality. This review is completed with the study of different types of accessibility measures including recent work on timegeography measures of accessibility.
    Date: 2014–04–02
  2. By: Henrik Andersson (Toulouse School of Economics (LERNA)); Arne Risa Hole (University of Sheffield); Mikael Svensson (Karlstad University)
    Abstract: This study elicits individual preferences for reducing morbidity and mortality risk in the context of an infectious disease (campylobacter) using choice experiments. Respondents are in the survey asked to choose between different policies that, in addition to the two health risks, also vary with respect to source of disease being targeted (food or water), when the policy takes place (in time), and the monetary cost. Our results in our baseline model are in line with expectations; respondents prefer the benefits of the program sooner than later, programs that reduce both the mortality and morbidity risk, and less costly programs. Moreover, our results suggest that respondents prefer water- compared with food-safety programs. However, a main objective of this study is to examine scope sensitivity of mortality risk reductions using a novel approach. Our results from a split-sample design suggest that the value of the mortality risk reduction, defined as the value of a statistical life, is SEK 3 177 (USD 483 million) and SEK 50 million (USD 8 million), respectively, in our two sub-samples. This result cast doubt on the standard scope sensitivity tests in choice experiments, and the results also cast doubt on the validity and reliability of VSL estimates based on stated preference (and revealed preference) studies in general. This is important due to the large empirical literature on non-market evaluation and the elicited values' central role in policy making, such as benefit-cost analysis.
    Keywords: choice experiments; morbidity risk; mortality risk; scope sensitivity; willingness to pay
    JEL: D61 H41 I18 Q51
    Date: 2014–04
  3. By: Joseph Mercante; Penny Mok (The Treasury)
    Abstract: In this paper we estimate labour supply using a discrete choice approach for single men, single women and single parents and a joint labour supply equation for couples in New Zealand. The data are based on pooled cross-sectional data from the Household Economic Survey over 2006/07 to 2010/11. We allow singles to choose from eleven discrete hours whilst couples choose from 66 combined working hour choices. Net incomes at all possible discrete working-hours are calculated using Treasury’s TAXWELL microsimulation model. For non-workers, net incomes are estimated based on an imputed wage. In order to fit the model to the observed working hour distribution we include a fixed cost of working parameter and we explicitly take account of observed and unobserved heterogeneity in the data. We find that the coefficient estimates of the labour supply equations mostly accord with expectations and are reasonably comparable with previously estimated equations for New Zealand. Using the equations we find that the labour supply predictions fit the observed data reasonably well. However, despite the inclusion of a fixed cost of working parameter, the peak working hours of around 40 hours per week in the observed data is under-predicted by the models, while part-time hours of work remain over-predicted. We compute labour supply elasticities from the estimated parameters which show that single parents and single women are the most responsive, whilst partnered men and single men are the least responsive.
    Keywords: labour supply; discrete choice; random utility; multinomial logit
    JEL: C25 J22
    Date: 2014–04
  4. By: Zhang, Junfu (Clark University); Zheng, Liang (Central University of Finance and Economics)
    Abstract: It is difficult to determine whether ghettos are good or bad, partly because racial segregation may have some effects that are unobservable. To overcome this challenge, we present a migration choice model that allows for estimating the overall effects of racial segregation. The key idea underlying our empirical approach is that if segregation indeed has a negative overall effect, migrants should be willing to give up some earnings to avoid living in segregated cities. Using decennial census data from 1980 to 2000, we provide new evidence that ghettos are bad. It is shown that both black and white migrants prefer to live in less segregated cities. For example, for a one-percentage-point reduction in the dissimilarity index, the estimated marginal willingness to pay of blacks is $436 (in 1999 dollars) in 2000. Among whites, this marginal willingness to pay is $301.
    Keywords: residential segregation, internal migration, discrete choice model
    JEL: O15 R12 R23
    Date: 2014–04
  5. By: Anabela Botelho (NIMA, Universidade do Minho); Isabel Dinis; Lina Sofia Lourenço-Gomes (University of Trás-os-Montes and Alto Douro); Jorge Moreira (CERNAS, Instituto Politécnico de Coimbra, Escola Superior Agrária de Coimbra); Lígia M.Costa Pinto (NIMA, Universidade do Minho)
    Abstract: The identification and characterization of consumers’ preferences for agricultural products may constitute a valuable tool for producers in identifying market niches for their current production and to plan activity choice for the future. Traditional varieties of fruits and vegetables have been subject to some scrutiny in this respect. However, but for a few studies, consumers’ preferences for tomatoes have rarely been studied. Using the contingent valuation methodology applied to a panel of six different varieties of tomatoes (three national varieties, and three foreign varieties), the present paper provides evidence concerning the most relevant determinants of consumers’ willingness to pay, controlling for place and mode of production of the tomatoes’ varieties. In addition, the study elicits consumers’ rating of these varieties with respect to appearance, taste, smell and texture. Based on our multivariate results, the estimated market price premium for national varieties of tomatoes is 35% relatively to foreign varieties.
    Keywords: Valuation methods, Agro-food economics, elicitation of consumer preferences
    JEL: Q20 Q50 Q10
    Date: 2014–01
  6. By: Donna, Javier; Espin-Sanchez, Jose
    Abstract: We explore a particular historical episode that switched from a market institution (auctions) to a non-market institution (fixed quotas with a ban on trading) to allocate water. This water is used by farmers for agricultural purposes; some of the farmers are liquidity constraints. We present a model in which farmers face liquidity constraints to explain why the change took place. From a positive perspective, we show that demand is underestimated if these liquidity constraints are not taken into account. We use a dynamic discrete choice model to estimate demand during the auction period; we also estimate the probability of being liquidity constrained by a farmer. From a normative perspective, auctions achieve the first-best allocation only in the absence of liquidity constraints; the quota achieves the first best allocation only if farmers are homogeneous in productivity. We compute the welfare under both institutions using the estimated parameters of the structural model.
    Keywords: Organization of Production, Institutions, Financial Markets, Market Efficiency, Water
    JEL: D02 D53 G14 L23 Q25
    Date: 2014–02
  7. By: G. Fiorentini; G. Ragazzi; S. Robone
    Abstract: This paper considers the influence of patients’ characteristics on their evaluation of a health system’s responsiveness, that is, a system’s ability to respond to the legitimate expectations of potential users regarding non-health enhancing aspects of care (Valentine et al. 2003a). Since responsiveness is evaluated by patients on a categorical scale, their selfevaluation can be affected by the phenomenon of reporting heterogeneity (Rice et al. 2012). A few studies have investigated how standard socio-demographic characteristics influence the reporting style of health care users with regard to the question of the health system’s responsiveness (Sirven et al. 2012, Rice et al. 2012). However, we are not aware of any studies that focus explicitly on the influence that both the patients’ state of health and their experiencing of pain have on the way in which they report on system responsiveness. This paper tries to bridge this gap by using data regarding a sample of patients hospitalized in four Local Health Authorities (LHA) in Italy’s Emilia-Romagna region between 2010 and 2012. These patients have evaluated 27 different aspects of the quality of care, concerning five domains of responsiveness (communication, social support, privacy, dignity and quality of facilities). Data have been stratified into five sub-samples, according to these domains. We estimate a generalized ordered probit model (Terza, 1985), an extension of the standard ordered probit model which permits the reporting behaviour of respondents to be modelled as a function of certain respondents’ characteristics, which in our analysis are represented by the variables “state of health” and “pain”. Our results suggest that unhealthier patients are more likely to report a lower level of responsiveness, all other things being equal, while patients experiencing pain are more likely to make use of the extreme categories of responsiveness, that is, to choose the category “completely dissatisfied” or the category “completely satisfied”. These results hold across all five domains of responsiveness.
    JEL: I1 I11 I19 C50 C25
    Date: 2014–03
  8. By: S. Robone; G. Fiorentini; M. A. Nicoli; S. Rodella
    Abstract: The release of the World Health Report 2000 has brought to the fore the concept of responsiveness as an indicator of health system performance. Responsiveness relates to a system’s ability to respond to the legitimate expectations of potential users about non-health enhancing aspects of care (Valentine et al. 2003). A few studies have investigated how standard socio-demographic characteristics (such as income or education) have an influence on the evaluation of responsiveness by health care users (Puentes Rosas et al. 2006, Sirven et al. 2012, Rice et al. 2012). However, we are not aware of any study investigating the relationship between the frequency with which patients use health services and their evaluation of responsiveness. This paper narrows this gap by using data regarding a sample of patients hospitalized in 9 hospitals of Emilia Romagna, a Region of Italy. The data have been collected by the Agency for Health Care and Social Services of Emilia Romagna between January 2010 and December 2012. We investigate a representative sample of about 2500 in-patients, who have been asked to evaluate 29 different aspect of quality of care which refer to 6 domains of health system responsiveness (communication, social support, privacy, dignity, waiting times and quality of facilities). We make use of this structure of the data by adopting a panel data regression model. The adoption of a panel model helps in controlling for individual heterogeneity, which otherwise could bias our results. Given that responsiveness is evaluated on an ordinal and categorical scale (going from “very dissatisfied” to “very satisfied”) we estimate a panel ordered logit model. Our results suggest that if patients have already been hospitalized in the same ward over the last 5 years they evaluate responsiveness more positively compared to patients who have never been hospitalized before. However, this effect is statistically significant only if patients have been hospitalized in the last 6 months. More generally, the use of a proper methodology to investigate responsiveness at hospital level can allow a better identification of area of intervention for investments in staff training; moreover, it can allow to modify hospital characteristics which have a negative impact on patients’ reporting of responsiveness.
    JEL: I11 I19 C50
    Date: 2014–03
  9. By: Julio Rosa; Pierre Mohnen
    Abstract: On the one hand, firms prefer to perform R&D in an open mode (letting R&D be performed extramurally or even selling their R&D services) to benefit from knowledge spillovers and complementarities between internal and external R&D. On the other hand, they may also like to perform R&D in a closed mode (funding and executing their R&D intramurally) to minimize outgoing externalities. We examine the dynamic process by which firms change the way of doing R&D and how these strategic choices of doing R&D affect their productivity growth. This study is based on the Statistics Canada Research and Development in Canadian Industry survey (RDCI), which collects data on R&D performed in the business sector in Canada. The paper is based on data for the period 1997 to 2006. The panel dimension of the data allows to control for unobserved characteristics of R&D performers by estimating a multinomial Logit model with unobserved heterogeneities using maximum simulated likelihood (MSL) method. Les firmes sont tiraillées entre deux façons de faire de la R-D. D’un côté, elles préfèrent faire la R-D de manière ouverte (en faisant faire de la R-D extramuros ou même en vendant des services de R-D) afin de bénéficier d’externalités de connaissance et de complémentarités entre la R-D interne et la R-D externe. D’un autre côté, elles préconisent de faire la R-D en mode fermé (en faisant de la recherche intramuros et en se finançant sur base de fonds propres ou de subventions) afin de minimiser les fuites de connaissance. Dans cette étude, nous examinons la dynamique des choix quant à la façon de faire de la recherche et l’effet de ces choix sur les rendements de celle-ci. Nous nous basons sur les données de l’enquête de Statistique Canada sur la recherche et développement dans l’industrie canadienne (RDIC) pour la période 1997-2006. La dimension panel de la base de données nous permet de contrôler pour l’hétérogénéité individuelle inobservée dans l’estimation d’un modèle Logit multinomial dynamique à partir de la méthode du maximum de vraisemblance simulé.
    Keywords: R&D; State Dependence; Dynamic Multinomial Logit; Panel-data; Maximum Simulated Likelihood; Open Innovation, persistance, modèle Logit multinomial dynamique, données panel, maximum de vraisemblance simulé, innovation ouverte
    Date: 2013–11–01
  10. By: Hammond, Peter J (University of Warwick); Liberini, Federica (Zurich, Switzerland); Proto, Eugenio (University of Warwick)
    Abstract: Using British Household Panel Survey data, for subjects not reporting the highest permitted satisfaction level, we show that the conditional income distribution given a higher reported level of life satisfaction rst-order stochastically dominates the corresponding conditional distribution given any lower satisfaction level. Subjects reporting the highest satisfaction level, however, have an income distribution dominated by distributions for some less satised individuals. Interestingly, this \top anomaly" is undetectable by standard ordered probit analysis. An alternative binary probit model for reporting maximal satisfaction suggests a possible explanation: more educated subjects not only tend to have higher income, but are also less likely to report maximal satisfaction.
    Date: 2013
  11. By: Ali Fakih; Pascal L. Ghazalian
    Abstract: This paper examines the implications of firm-related and national factors for Female Labour Force Participation (FLFP) rates in manufacturing firms located in the Middle East and North Africa (MENA) region. The empirical investigation uses data derived from the World Bank’s Enterprise Surveys database and applies fractional logit models to carry out the estimations. The results reveal positive implications of many firm-related factors, mainly private foreign ownership and exporting activities, for FLFP rates. National factors, such as economic development and gender equality, are also found to promote FLFP rates. These effects are generally found to be more important for women’s overall labour participation rates than for women’s non-production labour participation rates.
    Keywords: Female labour force participation, fractional logit model, manufacturing firms, MENA region,
    JEL: J16 J21 J23 J82
    Date: 2013–12–01
  12. By: Alain Jousten; Mathieu Lefebvre; Sergio Perelman
    Abstract: Many Belgian retire well before the statutory retirement age. Numerous exit routes from the labor force can be identified: old-age pensions, conventional early retirement, disability insurance, and unemployment insurance are the most prominent ones. We analyze the retirement decision of Belgian workers adopting an option value framework, and pay special attention to the role of health status. We estimate probit models of retirement using data from SHARE. The results show that health and incentives matter in the decision to exit from the labor market. Based on these results, we simulate the effect of potential reforms on retirement.
    JEL: H55 J21 J26
    Date: 2014–04

This nep-dcm issue is ©2014 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.