nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2016‒03‒23
nine papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  2. Income-comparison Attitudes in the US and the UK: Evidence from Discrete-choice Experiments By Hitoshi Shigeoka; Katsunori Yamada
  3. Putting a price tag on security: Subjective well-being and willingness-to-pay for crime reduction in Europe By Brenig, Mattheus; Proeger, Till
  4. Measuring fuel poverty in France: Which households are the most fuel vulnerable? By Bérangère Legendre; Olivia Ricci
  5. Assessment of Post-merger Coordinated Effects: Characterization by Simulations By Ivaldi, Marc; Lagos, Vicente
  6. EU Accession and Foreign Owned Firms in Bulgaria By Zadia M. Feliciano; Nadia Doytch
  7. Predicting US banks bankruptcy: logit versus Canonical Discriminant analysis By Zeineb Affes; Rania Hentati-Kaffel
  8. Cost benefit analysis and the environment: How to best cover impacts on biodiversity and ecosystem services By Anil Markandya
  9. Intrageneration Poverty Dynamics in Indonesia: Households’ Welfare Mobility Before, During, and After the Asian Financial Crisis By Dartanto, Teguh; Otsubo, Shigeru

  1. By: Stijn Baert; Bart Cockx; Matteo Picchio (-)
    Abstract: A dynamic discrete choice model is set up to estimate the effects of grade retention in high school, both in the short- (end-of-year evaluation) and long-run (drop-out and delay). In contrast to regression discontinuity designs, this approach captures treatment heterogeneity and controls for grade-varying unobservable determinants. A method is proposed to deal with initial conditions and with partial observability of the track choices at the start of high school. Forced track downgrading is considered as an alternative remedial measure. In the long-run, grade retention and its alternative have adverse effects on schooling outcomes and, more so, for less able pupils.
    Keywords: Education, grade retention, track mobility, dynamic discrete choice models, heterogeneous treatment effects.
    JEL: C33 C35 I21
    Date: 2015–12
  2. By: Hitoshi Shigeoka; Katsunori Yamada
    Abstract: Economists have long been aware of utility externalities such as a tendency to compare own income with others'. If welfare losses from income comparisons are significant, any governmental interventions that alter such attitudes may have large welfare consequences. We conduct an original online survey of discrete-choice questions to estimate such attitudes in the US and the UK. We find that the UK respondents compare incomes more than US respondents do. We then manipulate our respondents with simple information to examine whether the attitudes can be altered. Our information treatment suggesting that comparing income with others may diminish welfare even when income levels increase makes UK respondents compare incomes more rather than less. Interestingly, US respondents are not affected at all. The mechanism behind the UK results seems to be that our treatment gives moral license to make income comparisons by providing information that others do so.
    JEL: C9 D1 D3
    Date: 2016–02
  3. By: Brenig, Mattheus; Proeger, Till
    Abstract: Using information on life satisfaction and crime from the European Social Survey, we apply the life satisfaction approach (LSA) to determine the relationship between subjective well-being (SWB), income, victimization experience, fear of crime and various regional crime rates across European regions, while controlling for potentially confounding socio-economic variables. We show that fear of crime, criminal victimization and the average regionally perceived fear of crime significantly reduce life satisfaction across Europe. Building upon these results, we quantify the monetary value of improvements in public safety and its valuation in terms of individual well-being. The loss in satisfaction for victimized individuals corresponds to 21,790€. Increasing an average individual´s perception within his neighborhood from unsafe to safe yields a benefit equivalent to 12,700€. Our results regarding crime and SWB in Europe largely resemble previous results for different countries and other criminal contexts, whereby using the LSA as a valuation method for public good provision yields similar results as stated preference methods and considerably higher estimates than revealed preference methods.
    Keywords: crime rate,fear of crime,life satisfaction approach,subjective well-being,willingness-to-pay
    JEL: D10 H41 H56 I31
    Date: 2016
  4. By: Bérangère Legendre (IREGE - Institut de Recherche en Gestion et en Economie - USMB [Université de Savoie] [Université de Chambéry] - Université Savoie Mont Blanc); Olivia Ricci (CEMOI - Centre d'Économie et de Management de l'Océan Indien - Université de la Réunion - IAE - Institut d'Administration des Entreprises - Université de la Réunion)
    Abstract: Fuel poverty is a growing concern in France. Following the hike in energy prices that started in 2004, the problem of energy affordability for low-income households entered the political debate with the " Grenelle de l " environnement " in 2007. According to the standard UK definition (10% ratio) 3.8 million households were subject to fuel poverty in France in 2006. We question the way fuel poverty is currently measured and compare the impact of alternative measurement approaches on the extent and composition of fuel poverty in France. Then, we identify and characterize vulnerable households that are not ordinarily poor, but can be pushed into poverty because of their fuel bills. A logit, a clog log and a mixed effect logit model are used to analyze which factors influence the probability of vulnerable households to fall into poverty. The study indicates that the proportion of fuel poor people and their characteristics differ significantly depending on the fuel poverty measure chosen. The econometric results show that the probability of falling into poverty is higher for those who are retired living alone, rent their home, use an individual boiler for heating, cook with butane or propane and have poor roof insulation. Current French fuel poverty reduction policies appear to be inappropriate given our conclusions.
    Keywords: Fuel poverty,vulnerable households,poverty indicators,clog log model
    Date: 2015
  5. By: Ivaldi, Marc; Lagos, Vicente
    Abstract: This paper aims to evaluate the coordinated effects of horizontal mergers by simulating its impact on firms’ critical discount factors. The simulation setting considers a model with a random coefficient discrete choice demand and heterogeneous price-setting firms on the supply side. The results suggest that mergers strengthen the incentives to collude among merging parties, but weaken the incentives of non-merging parties. In addition, while the magnitude of this impact is moderate for the latter, it can be substantial for merging parties. Finally, general policy lessons regarding the assessment of the magnitude of these effects can be drawn from the results.
    Keywords: Assessment - Collusion - Coordinated effects - Critical Discount Factor - Merger Simulation
    Date: 2016–03
  6. By: Zadia M. Feliciano; Nadia Doytch
    Abstract: Bulgaria signed the Europe Association Agreement (EAA) in 1995 and the European Union accession treaty in 2005. Accession had the effect of increasing FDI in Bulgaria. We analyze World Bank BEEPS firm level data for 2007 to better understand characteristics and performance of foreign firms in Bulgaria. We estimate linear probability and logit models to determine the likelihood a firm is foreign in Bulgaria. Regressions show foreign manufacturing firms in Bulgaria are larger than domestic firms, have lower capital to labor ratios and are more likely to export. Foreign service sector firms are larger than domestic firms, have lower capital to labor ratios, are more likely to export and to locate in Sofia, the capital. Our analysis points to limited success of foreign firms in Bulgaria. Regressions show foreign manufacturing firms do not have higher sales growth and made less capital investments than domestic firms. Foreign firms in the service sector did not experience faster sales growth or had greater capital investments than domestic firms. Institutional indicators show manufacturing and service sector firms with larger fractions of exports relative to sales had a greater number of visits from tax officials. This suggests that exporting firms receive larger scrutiny than other firms, which represents a challenge to foreign firms in Bulgaria.
    JEL: F15 F21 F23
    Date: 2016–01
  7. By: Zeineb Affes (Centre d'Economie de la Sorbonne); Rania Hentati-Kaffel (Centre d'Economie de la Sorbonne)
    Abstract: Using a large panel of US banks over the period 2008-2013, this paper proposes an early-warning framework to identify bank leading to bankruptcy. We conduct a comparative analysis based on both Canonical Discriminant Analysis and Logit models to examine and to determine the most accurate of these models. Moreover, we analyze and improve suitability of models by comparing different optimal cut-off score (ROC curve vs theoretical value). The main conclusions are: i) Results vary with cut-off value of score, ii) the logistic regression using 0.5 as critical cut-off value outperforms DA model with an average of correct classification equal to 96.22%. However, it produces the highest error type 1 rate 42.67%, iii) ROC curve validation improves the quality of the model by minimizing the error of misclassification of bankrupt banks: only 4.42% in average and exhibiting 0% in both 2012 and 2013. Also, it emphasizes better prediction of failure of banks because it delivers in mean the highest error type II 8.43%
    Keywords: Bankruptcy prediction; Canonical Discriminant Analysis; Logistic regression; CAMELS; ROC curve; Early-warning system
    JEL: G21 G33 C25 C38 C53
    Date: 2016–02
  8. By: Anil Markandya
    Abstract: There are now a large number of valuation studies on the benefits of biodiversity and on ecosystem services, the services provided by different ecosystems (ESS). Both ideas have been used to elicit values from nature but in recent years the research community has focussed on ESS as the main organising framework, with some additional use of the biodiversity concept to value entities that have intrinsic value and are of an extraordinary nature. Estimates are available for the services from most habitats, by type of ecosystem service, usually expressed in USD per hectare per year. Coverage varies by habitat and region, as does the quality of the assessment, but it is possible now to carry out an estimation of changes in values for a number of ecosystem services a result of the introduction of a new policy or of a physical investment that modifies the ecosystem. While this is a positive development, there remain some issues to be resolved. One is the possibility of double-counting of services when using the standard categories of provisioning, regulating/supporting and cultural ESS. Regulating and supporting services are the basis of the provisioning services and so value estimates for the two cannot always be added up. For example, air pollution absorption is often valued using the cost of alternative ways of reducing the pollutants from the atmosphere while recreation is often valued in terms of willingness-to-pay (WTP) through stated preference methods.
    Keywords: environmental policy, biodiversity, cost-benefit analysis, ecosystem services
    JEL: H43 Q51 Q54 Q57 Q58
    Date: 2016–03–09
  9. By: Dartanto, Teguh; Otsubo, Shigeru
    Abstract: When the economic crisis hit in 1998, and economic growth dropped by 13.7 percent; exacerbated by domestic political turbulence, poverty figures sharply rose from 17.47 percent to 24.20 percent. It began to decline again as the economy quickly recovered from the crisis. The above details demonstrate that poverty is not a pure static phenomenon, but rather is dependent on dynamic characteristics that easily change over time. Households could move into (or out of) poverty in response to fluctuations in the economy. This study then aims to analyze the determinants of households’ shifting welfare during the periods before, during and after the Asian financial crisis in Indonesia. Applying the spell approach of poverty experience and observing four waves of IFLS (Indonesian Family Life Survey) balanced panel datasets, we find that during 1993-1997 (pre-crisis) households could be classified as chronically poor (6.14 percent), transient poor (-) (6.31 percent), transient poor (+) (10.58 percent) and never poor (76.96 percent). However, during 1997-2000 (crisis), the probability of being transient poor (-) had jumped drastically from 5 percent (pre-crisis) to 14 percent (during the crisis). In the post crisis period, roughly 86 percent of the previously poor households could move out of poverty. This study also confirmed that the probability of being poor in the next period highly depends on past experiences with poverty. Moreover, reducing probability of being chronically poor by about half from 4.6 percent to 2.2 percent needs almost fifteen years. Furthermore, our estimations using the ordered logit model confirm that determinants of poverty dynamics include educational attainment, size of the household, share of education expenditure, distance to public transportation, ownership of livestock and liquid assets, and the impact suffered from earthquakes.
    Keywords: chronic poor , transient poor , poverty dynamics , panel data , Asian financial , crisis , Indonesia
    Date: 2016–03–08

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.