nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2015‒05‒22
thirteen papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. What Factors Affect Doctors' Hours Decisions: Comparing Structural Discrete Choice and Reduced-Form Approaches By Kalb, Guyonne; Kuehnle, Daniel; Scott, Anthony; Cheng, Terence Chai; Jeon, Sung-Hee
  2. Valuing malaria morbidity: Results from a global metaanalysis By Y Mehmet Kutluay; Roy Brouwer; Richard S. J. Tol
  3. Attitudes towards honey among Italian consumers: a choice experiment approach By Cosmina, Marta; Gallenti, Gianluigi; Marangon, Francesco; Troiano, Stefania
  4. Consumers’ Willingness to Pay for Renewable Energy: A Meta-Regression Analysis By Ma, Chunbo; Rogers, Abbie A.; Kragt, Marit E.; Zhang, Fan; Polyakov, Maksym; Gibson, Fiona; Chalak, Morteza; Pandit, Ram; Tapsuwan, Sorada
  5. Mortgage market, housing tenure choice and unemployment By Gaetano Lisi
  6. Using choice experiments to assess the costs of supplying carbon offsets in beef production systems By Gowen, Rebecca
  7. How Much Do Consumers Value PDO Certifications? Estimates of WTP for PDO Dry-Cured Ham in Italy By Garavaglia, Christian; Mariani, Paolo
  8. Relationship between health status and recycling rates: Evidence from Great Britain By Giovanis, Eleftherios; Ozdamar, Oznur
  9. Weighted pairwise likelihood estimation for a general class of random effects models By Vassilis G. S. Vasdekis; Dimitris Rizopoulos; Irini Moustaki
  10. How do speed and security influence consumers' payment behavior? By Schuh, Scott; Stavins, Joanna
  11. Do patients choose hospitals that improve their health? By Nils Gutacker; Luigi Siciliani; Giuseppe Moscelli; Hugh Gravelle
  12. Como a interação universidade-empresa é remunerada no Brasil: evidências dos grupos de pesquisa do CNPQ By Márcia Siqueira Rapini; Vanessa Parreiras de Oliveira; Thiago Caliari
  13. State Dependence in Welfare Receipt: Transitions Before and After a Reform By Riphahn, Regina T.; Wunder, Christoph

  1. By: Kalb, Guyonne (Melbourne Institute of Applied Economic and Social Research); Kuehnle, Daniel (University of Erlangen-Nuremberg); Scott, Anthony (Melbourne Institute of Applied Economic and Social Research); Cheng, Terence Chai (University of Adelaide); Jeon, Sung-Hee (Statistics Canada)
    Abstract: Few papers examine the pecuniary and non-pecuniary determinants of doctors' labour supply despite substantial predicted shortages in many OECD countries. We contribute to the literature by applying both a structural discrete choice and a reduced-form approach. Using detailed survey data for Australian physicians, we examine how these different modelling approaches affect estimated wage elasticities at the intensive margin. We show that all modelling approaches predict small negative wage elasticities for male and female General Practitioners (GPs) and specialists. Our detailed subgroup analysis does not reveal particularly strong responses to wage increases by any specific group. We show that the translog and Box-Cox utility functions outperform the quadratic utility function. Exploiting the advantages of the structural discrete choice model, we examine short-term effects at the intensive margin by calculating labour supply changes in response to 5 and 10% wage increases. The results show that such wage increases substantially reduce the full-time equivalent supply of male GPs, and to a lesser extent of male specialists and female GPs, but not of female specialists.
    Keywords: labour supply, discrete choice model, wage elasticity, health workforce, MABEL
    JEL: I11 J22 J44 J21
    Date: 2015–05
  2. By: Y Mehmet Kutluay (Department of Environmental Economics, Institute for Environmental Studies, Vrije Universiteit, Amsterdam, The Netherlands; Tinbergen Institute, Amsterdam, The Netherlands); Roy Brouwer (Department of Environmental Economics, Institute for Environmental Studies, Vrije Universiteit, Amsterdam, The Netherlands); Richard S. J. Tol (Department of Economics, University of Sussex, UK; Institute for Environmental Studies, Vrije Universiteit, Amsterdam, The Netherlands; Department of Spatial Economics, Vrije Universiteit, Amsterdam, The Netherlands; Tinbergen Institute, Amsterdam, The Netherlands; CESifo, Munich, Germany)
    Abstract: The risk of malaria transmission worldwide is expected to increase with climate change. In order to estimate the welfare implications, we analyse the factors that explain willingness to pay to avoid malaria morbidity using a meta-analysis. We compare multiple regression models via a cross-validation exercise to assess best fit, the first in the meta-analysis literature to do so. Weighted random effects gives best fit. Confirming previous studies, we find that revealed preferences are significantly lower than stated preferences; and that there is no significant difference in the willingness to pay for policies that prevent (pre-morbidity) or treat malaria (post-morbidity). We add two new results to the morbidity literature. 1) Age has a non-linear impact on mean willingness to pay and 2) willingness to pay decreases if malaria policies target communities instead of individual households.
    Keywords: Malaria, Meta-analysis, Willingness-to-pay, Morbidity, Stated Preferences
    JEL: I10
    Date: 2015–05
  3. By: Cosmina, Marta; Gallenti, Gianluigi; Marangon, Francesco; Troiano, Stefania
    Keywords: Crop Production/Industries, Food Consumption/Nutrition/Food Safety,
    Date: 2015–03
  4. By: Ma, Chunbo; Rogers, Abbie A.; Kragt, Marit E.; Zhang, Fan; Polyakov, Maksym; Gibson, Fiona; Chalak, Morteza; Pandit, Ram; Tapsuwan, Sorada
    Abstract: Using renewable energy for domestic consumption has been identified as a key strategy by the Intergovernmental Panel on Climate Change to reduce greenhouse gas emissions. Critical to the success of this strategy is to know whether consumers are willing to pay to increase the proportion of electricity generated from renewable energy in their electricity portfolio. There are a number of studies in the literature that report a wide range of willingness to pay estimates. In this study, we used a meta-regression analysis to determine how much of the variation in willingness to pay reflects true differences across the population and how much is due to study design, such as survey design and administration, and model specification. The results showed that factors that influence willingness to pay in individual studies, such as renewable energy type, consumers’ socio-economic profile and consumers’ energy consumption patterns, explain less variation in willingness to pay estimates than the characteristics of the study design. We also found that consumers have significantly higher willingness to pay for electricity generated from solar or generic renewable energy source (i.e. not a specific source) than wind, hydro or biomass. Due to the effect of study design on willingness to pay, we recommend that policy makers exercise caution when interpreting and using willingness to pay results from primary studies.
    Keywords: meta-regression, renewable energy, green electricity, valuation, willingness to pay, Environmental Economics and Policy, Institutional and Behavioral Economics, Resource /Energy Economics and Policy, C53, D62, Q40, Q48, Q51,
    Date: 2015–06–05
  5. By: Gaetano Lisi (Centro di Analisi Economica CREAtività e Motivazioni)
    Date: 2015–03
  6. By: Gowen, Rebecca
    Keywords: Environmental Economics and Policy, Livestock Production/Industries,
    Date: 2015–02
  7. By: Garavaglia, Christian; Mariani, Paolo
    Abstract: This study investigates consumers’ preferences and WTP for PDO certifications. First, the paper proposes the use of a new index in food studies to measure WTP. We focus on dry-cured ham in Italy. Our results add a geographical dimension to studies of consumer preferences by providing evidence of the existence of differences based on place of residence. Consumers who live in the same area where certified ham is produced are willing to pay a lower premium price than consumers living farther away are willing to pay: the closer consumers live to the area of production of the certified product, the less they refer to extrinsic certification cues.
    Keywords: Agricultural and Food Policy, Community/Rural/Urban Development, Consumer/Household Economics, Food Consumption/Nutrition/Food Safety,
    Date: 2015–04
  8. By: Giovanis, Eleftherios; Ozdamar, Oznur
    Abstract: This study explores the relationship between self-reported health status and recycling rates in Great Britain. The estimates are based on the data from the British Household Panel Survey (BHPS). The effects of recycling rates on individuals’ health status with a scale from 1- excellent- to 5-very poor- are estimated and their monetary values are calculated. In addition, the non-movers sample is considered in order to reduce endogeneity. Three approaches are followed. The first approach refers to the panel Probit-OLS, while the second approach is the ordered Probit model with random effects. The third approach refers to a dynamic panel regression estimated with the system Generalized Methods of Moments (GMM). The average marginal willingness-to-pay (MWTP) for a one per cent increase in recycling rates ranges between is £470-£800 per year. Moreover, other determinants play significant role on health status such as education, marital status, age, job status, age and weather conditions among others. The originality of this paper is that the relationship between self-reported health status and recycling rates using micro-level panel data is explored. Moreover, the reression analysis controls for various demographic, regional and meteorological factors. Finally, this is the first study presenting three different panel estimates to deal with the potential endogeneity of the pollution measure which is derived from recycling. Using fixed effects the regional time invariant characteristics are controlled, while the dynamic model allows controlling for time varying unobservables.
    Keywords: Environmental valuation; Panel data; Recycling; Self-reported health status
    JEL: I31 Q51 Q53 Q54
    Date: 2014
  9. By: Vassilis G. S. Vasdekis; Dimitris Rizopoulos; Irini Moustaki
    Abstract: Models with random effects/latent variables are widely used for capturing unobserved heterogeneity in multilevel/hierarchical data and account for associations in multivariate data. The estimation of those models becomes cumbersome as the number of latent variables increases due to high-dimensional integrations involved. Composite likelihood is a pseudo-likelihood that combines lower-order marginal or conditional densities such as univariate and/or bivariate; it has been proposed in the literature as an alternative to full maximum likelihood estimation. We propose a weighted pairwise likelihood estimator based on estimates obtained from separate maximizations of marginal pairwise likelihoods. The derived weights minimize the total variance of the estimated parameters. The proposed weighted estimator is found to be more efficient than the one that assumes all weights to be equal. The methodology is applied to a multivariate growth model for binary outcomes in the analysis of four indicators of schistosomiasis before and after drug administration.
    Keywords: categorical data; composite likelihood; generalized linear latent variable models; longitudinal data
    JEL: C1
    Date: 2014–10
  10. By: Schuh, Scott (Federal Reserve Bank of Boston); Stavins, Joanna (Federal Reserve Bank of Boston)
    Abstract: The Federal Reserve Financial Services (FRFS) strategic plan for 2012-2016 named improvements in the end-to-end speed and security of the payment system as two of its policy initiatives. End-to-end in this context means that for the first time end-users are explicitly included. Earlier versions of the strategy plan were circulated for public comment, and the feedback received by FRFS specifically identified a need for further research. This brief draws upon new data from the 2013 Survey of Consumer Payment Choice and employs econometric modeling and simulation to complement FRFS-commissioned market research on end users' preferences. The authors' approach relies on revealed preference to incorporate insight into consumers' actual behavior, not just their attitudes, and their models employ a two-stage technique, estimating, first, the influence of the simulated improvements in speed and in security on the adoption of the payment instruments considered, and, second, the influence on the choice of which of the adopted payment instruments to use. The final version of the strategic plan is currently under discussion by Federal Reserve policymakers, so all the policies and strategies discussed in this brief are preliminary.
    JEL: D12 D14 E58
    Date: 2015–02–05
  11. By: Nils Gutacker (Centre for Health Economics, University of York, UK); Luigi Siciliani (Department of Economics and Related Studies, University of York, UK); Giuseppe Moscelli (Centre for Health Economics, University of York, UK); Hugh Gravelle (Centre for Health Economics, University of York, UK)
    Abstract: Many health care systems collect and disseminate information on provider quality in order to facilitate patient choice and induce competitive behaviour amongst providers. The Department of Health in England has recently mandated the collection of patient-reported health outcome measures (PROMs) for the purpose of performance assessment and consumer information. This is the first attempt to routinely measure the gain in health that patients experience as the result of care and thus offer a more comprehensive picture of hospital quality than existing ‘failure measures’ such as mortality or readmission rates. In this paper we test whether hospital demand responds to hospital quality measures based on health gains in addition to more conventional measures. We estimate hospital choice models for elective hip replacement surgery using rich administrative data for all publicly-funded patients in the English NHS in 2010-2012. Our focus is on two key aspects of hospital choice: 1) the extent to which patients are more likely to choose hospitals which are expected to achieve larger improvements in patients’ health and 2) whether patients’ response to quality differs with their morbidity, as measured by pre-operative health status, and other characteristics such as age or income deprivation. In order to address potential endogeneity bias we implement an empirical strategy based on lagged explanatory variables, hospital fixed effects and a control group design based on demand for emergency hip replacement. Our results suggest that hospitals can increase demand by 9% if they increase the average health gains that patients experience by one standard deviation. Hospital demand has a higher elasticity with respect to average health gains than emergency readmission or mortality rates. Elective patients are twice as willing as emergency hip replacement patients to travel further for an increase in quality
    Keywords: Patient choice, hospital demand, demand elasticity, quality of care, health outcomes
    Date: 2015–05
  12. By: Márcia Siqueira Rapini (Cedeplar-UFMG); Vanessa Parreiras de Oliveira (IE/UNICAMP); Thiago Caliari (UNIFAL/MG)
    Abstract: The aim of this paper is to investigate the funding of university-industry interactions in Brazil from DGP/CNPQ. The responses of 2,726 groups of interactive research relating to Census 2008 were analyzed. Analysis shows that the most frequent remuneration were the transfer of financial and material resources and also to a lesser extent remuneration based in the generation and exchange of tacit knowledge and staff exchanges. Through a multinomial logit econometric model the characteristics that influence the type of remuneration in university-firm cooperation were analyzed, and the results suggest that scientific excellence, the research group knowledge area, the mode of interaction and the industrial sector impact differently on the type of remuneration established.
    Keywords: funding, university-firms interactions, research groups, Brazil
    JEL: O30
    Date: 2014–12
  13. By: Riphahn, Regina T. (University of Erlangen-Nuremberg); Wunder, Christoph (Martin-Luther University, Halle-Wittenberg)
    Abstract: We study state dependence in welfare receipt and investigate whether welfare transitions changed after a welfare reform. Using data from the German Socio-Economic Panel, we apply dynamic multinomial logit estimators and find that state dependence in welfare receipt is not a central feature of the German welfare system. We find that welfare transitions changed after the reform: transitions from welfare to employment became more likely and persistence in welfare and inactivity declined. We observe a large relative increase in transitions from employment to welfare. Immigrants' responsiveness to the labor market situation increased after the reform.
    Keywords: social assistance, state dependence, unemployment benefit II, immigration, dynamic multinomial logit
    JEL: I38 J61
    Date: 2015–05

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.