nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2013‒12‒15
eight papers chosen by
Edoardo Marcucci
Universita' di Roma Tre

  1. Econometric Modelling of Social Bads By William H Greene; Mark N Harris; Preety Srivastava; Xueyan Zhao
  2. The European Crisis and Migration to Germany: Expectations and the Diversion of Migration Flows By Simone BERTOLI; Herbert BRÜCKER; Jesús FERNÁNDEZ-HUERTAS MORAGA
  3. Emerging market multinationals in the European Union – A location choice analysis By Hassan, Sohaib Shahzad; Jindra, Björn; Cantner, Uwe; Günther, Jutta
  4. State dependence in Swedish social assistance in the 1990s: What happened to those who were single before the recession? By Andrén, Daniela; Andrén, Thomas
  5. Underemployment among Mature Aged Workers in Australia By Jinjing Li; Alan S Duncan; Riyana Miranti
  6. Influences of infrastructure and attitudes to health on value of travel time savings in bicycle journeys By Björklund, Gunilla; Mortazavi , Reza
  7. Adverse selection and risk adjustment under imperfect competition By Normann Lorenz
  8. The influence of cost-effectiveness and other factors on NICE decisions By Helen Dakin; Nancy Devlin; Yan Feng; Nigel Rice; Phill O’Neill; David Parkin

  1. By: William H Greene (Economics Department, Stern School of Business, New York University (NYU)); Mark N Harris (School of Economics and Finance, Curtin University); Preety Srivastava (Department of Econometrics and Business Statistics, Monash University); Xueyan Zhao (Department of Econometrics and Business Statistics, Monash University)
    Abstract: When modelling 'social bads', such as illegal drug consumption, researchers are often faced with a dependent variable characterised by an excessive?amount of zero bservations. Building on the recent literature on hurdle and double-hurdle models, we propose a double-inflated modelling framework, where the zero observations are allowed to come from: non-participants; participant misreporters (who have larger loss functions associated with a truthful response); and infrequent consumers. Due to our empirical application, the model is derived for the case of an ordered discrete dependent variable. However, it is similarly possible to augment other such zero-inflated models (zero-inflated count models, and double-hurdle models for continuous variables, for example). The model is then applied to a consumer choice problem of cannabis consumption. As expected we find that misreporting has a significant (estimated) effect on the recorded incidence of marijuana. Specifically, we find that 14% of the zeros reported in the survey is estimated to come from individuals who have misreported their participation.
    Keywords: Ordered outcomes, discrete data, cannabis consumption, zero-inflated responses
    JEL: C3 D1 I1
    Date: 2013–07
  2. By: Simone BERTOLI (CERDI - Centre d'études et de recherches sur le developpement international - CNRS : UMR6587 - Université d'Auvergne - Clermont-Ferrand I); Herbert BRÜCKER (IAB - IAB - University of Bamberg); Jesús FERNÁNDEZ-HUERTAS MORAGA (IAE - FEDEA - CSIC)
    Abstract: The European crisis has diverted migration flows away from countries affected by the recession towards Germany. The diversion process creates a challenge for traditional discrete-choice models that assume that only bilateral factors account for dyadic migration rates. This paper shows how taking into account the sequential nature of migration decisions leads to write the bilateral migration rate as a function of expectations about the evolution of economic conditions in alternative destinations. Empirically, we incorporate 10-year bond yields as an explanatory variable capturing forward-looking expectations and apply our model to an empirical analysis of migration from the countries of the European Economic Association to Germany in the period 2006-2012. We show that disregarding alternative destinations leads to substantial biases in the estimation of the determinants of migration rates.
    Keywords: cerdi
    Date: 2013–12–04
  3. By: Hassan, Sohaib Shahzad; Jindra, Björn; Cantner, Uwe; Günther, Jutta
    Abstract: The European Union (EU) is one of the largest recipients of outward foreign direct investment (OFDI) from emerging economies. We apply a discrete choice model to analyze the location choice of emerging market firms in the EU27. In particular, we test to what extent these firms’ location choices are related to agglomeration economies and knowledge externalities because these have been suggested as potential sources for technological catching-up for emerging market firms. Our results indicate that emerging market firms’ location choices differ from the choices of other investors. Emerging market firms place, on average, a higher value on urbanization, diversification economies and sector-specific human resources. However, we find evidence for heterogeneity in the location choices of emerging market firms depending on the home region and the sector of investment.
    Keywords: Outward FDI, location choice, emerging economies, European Union, Spill-overs, Knowledge-seeking FDI
    JEL: F23
    Date: 2013–08–01
  4. By: Andrén, Daniela (Örebro University School of Business); Andrén, Thomas (Swedish Confederation of Professional Associations (Saco))
    Abstract: Using a dynamic discrete choice model that controls for unobserved heterogeneity and the initial conditions problem, we estimate the state dependence in Swedish social assistance for Swedish-born and foreign-born who were single in 1990 before the recession period started. The estimates of the structural state dependence for Swedish-born singles indicate that it is unaffected by the event of living together with a partner, and the effect is significantly lower for women than for men. For the foreign-born singles, the state dependence for those who stay single the whole decade is equally strong for men and women, and almost not affected when the foreign-born single started to live together with a foreign-born partner.
    Keywords: social assistance; state dependence; country of birth; singles; married/cohabitated; unobserved heterogeneity; initial conditions; dynamic random effects probit model; GHK simulator
    JEL: I30 I38 J18
    Date: 2013–12–09
  5. By: Jinjing Li (National Centre for Social and Economic Modelling (NATSEM), University of Canberra); Alan S Duncan (Bankwest Curtin Economics Centre (BCEC), Curtin University); Riyana Miranti (National Centre for Social and Economic Modelling (NATSEM), University of Canberra)
    Abstract: Underemployment is a serious and pervasive problem both in terms of its impact on those individuals affected, and for the economy as a whole. International research has found that those who experience periods of underemployment are more likely to have lower job satisfaction, higher job turnover, poorer mental and physical health and persistently lower earnings. Labour markets with high rates of underemployment are at risk of underutilisation of important skills. This paper explores the patterns of underemployment for mature aged workers in Australia, and seeks in particular to determine the principal factors that contribute to a heightened risk of underemployment. Importantly, our results point to a significant path dependency whereby previous periods of underemployment increase the propensity towards underemployment in the current period. Length: 29 pages
    Keywords: underemployment, labour supply transitions, baby boomers, mature aged workers, discrete choice models
    JEL: J01 J11 J21
    Date: 2013–06
  6. By: Björklund, Gunilla (VTI); Mortazavi , Reza (Dalarna University)
    Abstract: In this paper we investigate how attitudes to health and exercise in connection with cycling influence the estimation of values of travel time savings in different kinds of bicycle environments (mixed traffic, bicycle lane in the road way, bicycle path next to the road, and bicycle path not in connection with the road). The results, based on two Swedish stated choice studies, suggest that the values of travel time savings are lower when cycling in better conditions. Surprisingly, the respondents do not consider cycling on a path next to the road worse than cycling on a path not in connection to the road, indicating that they do not take traffic noise and air pollution into account in their decision to cycle. No difference can be found between cycling on a road way (mixed traffic) and cycling in a bicycle lane in the road way. The results also indicate that respondents that include health aspects in their choice to cycle have lower value of travel time savings for cycling than respondents that state that health aspects are of less importance, at least when cycling on a bicycle path. The appraisals of travel time savings regarding cycling also differ a lot depending on the respondents’ alternative travel mode. The individuals who stated that they will take the car if they do not cycle have a much higher valuation of travel time savings than the persons stating public transport as the main alternative to cycling.
    Keywords: Value of travel time savings; Cyclists; Infrastructure; Attitudes; Health
    JEL: R40
    Date: 2013–12–10
  7. By: Normann Lorenz
    Abstract: This paper analyzes the distortions of health insurers’ benefit packages due to adverse selection when there is imperfect competition. Within a discrete choice setting with two risk types, the following main results are derived: For intermediate levels of competition, the benefit packages of both risk types are distorted in the separating equilibrium. As the level of competition decreases, the distortion decreases for the low risk type, but increases for the high risk type; in addition, the number of insurers offering the benefit package for the low risk type increases. If the level of competition is low enough, a pooling equilibrium emerges, which generally differs from the Wilson-equilibrium. It is shown that these results have important implications for risk adjustment: For intermediate levels of competition, risk adjustment can be ineffective or even decrease welfare if it is not reasonably precise.
    Keywords: Adverse selection, discrete choice, risk adjustment
    JEL: I18
    Date: 2013
  8. By: Helen Dakin (Health Economics Research Centre, University of Oxford, UK); Nancy Devlin (Office of Health Economics, London, UK); Yan Feng (Office of Health Economics, London, UK); Nigel Rice (Centre for Health Economics and Department of Economics and Related Studies, University of York, UK); Phill O’Neill (Office of Health Economics, London, UK); David Parkin (Department of Primary Care and Public Health Sciences, King’s College London, UK)
    Abstract: Background: The National Institute for Health and Care Excellence (NICE) emphasises that cost-effectiveness is not the only consideration in health technology appraisal and is increasingly explicit about other factors considered relevant. Observing NICE decisions and the evidence considered in each appraisal allows us to ‘reveal’ its implicit weights. Objectives: This study aims to investigate the influence of cost-effectiveness and other factors on NICE decisions and to investigate whether NICE’s decision-making has changed through time. Methods: We build on and extend the modelling approaches in Devlin and Parkin (2004) and Dakin et al (2006). We model NICE’s decisions as binary choices: i.e. recommendations for or against use of a healthcare technology in a specific patient group. Independent variables comprised: the clinical and economic evidence regarding that technology; the characteristics of the patients, disease or treatment; and contextual factors affecting the conduct of health technology appraisal. Data on all NICE decisions published by December 2011 were obtained from HTAinSite []. Results: Cost-effectiveness alone correctly predicted 82% of decisions; few other variables were significant and alternative model specifications led to very small variations in model performance. The odds of a positive NICE recommendation differed significantly between musculoskeletal disease, respiratory disease, cancer and other conditions. The accuracy with which the model predicted NICE recommendations was slightly improved by allowing for end of life criteria, uncertainty, publication date, clinical evidence, only treatment, paediatric population, patient group evidence, appraisal process, orphan status, innovation and use of probabilistic sensitivity analysis, although these variables were not statistically significant. Although there was a non-significant trend towards more recent decisions having a higher chance of a positive recommendation, there is currently no evidence that the threshold has changed over time. The model with highest prediction accuracy suggested that a technology costing £40,000 per quality-adjusted life-year (QALY) would have a 50% chance of NICE rejection (75% at £52,000/QALY; 25% at £27,000/QALY). Discussion: Past NICE decisions appear to have been based on a higher threshold than the £20,000- £30,000/QALY range that is explicitly stated. However, this finding may reflect consideration of other factors that drive a small number of NICE decisions or cannot be easily quantified.
    Keywords: Health technology assessment; implicit weights; cost-effectiveness, National Institute for Health and Care Excellence (NICE); logistic regression
    Date: 2013–11

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.