nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2014‒06‒14
four papers chosen by
Edoardo Marcucci
Universita' di Roma Tre

  1. Cheaper electricity or a better river? Estimating fluvial ecosystem value in Southern France By Anna Créti; Federico Pontoni
  2. Banking Fragility in Colombia: An Empirical Analysis Based on Balance Sheets By Ignacio Lozano; Alexander Guarín
  3. The Effects of Non-binding Retail-price Recommendations on Consumer and Retailer Behavior By Lisa Bruttel
  4. Who is overeducated and why? Probit and dynamic mixed multinomial logit analyses of vertical mismatch in East and West Germany By Boll, Christina; Leppin, Julian Sebastian; Schömann, Klaus

  1. By: Anna Créti (Department of Economics, Ecole Polytechnique - CNRS : UMR7176 - Polytechnique - X, Leda-CGMP-Université Paris Dauphine - (-)); Federico Pontoni (IEFE - Università Bocconi and EconomiX - Paris Ouest Nanterre La Défense - (-))
    Abstract: In the next years, France will renew a consistent share of hydroelectric concessions, among which we find those insisting on the Aspe and its tributaries (for a total of almost 100 MW). Beauty contests will take place, where bidders will present offers for technical and environmental improvements, as well as a revenue sharing percentage for Local Authorities. This framework generates a potential trade-off between revenue-sharing and environmental improvement. Our work investigates this trade-off by means of a discrete choice experiment (DCE) to estimate people's preferences. The experiment has been conducted on a representative sample living in the Aspe valley. In our DCE, we translate the revenue sharing in an immediate rebate in the electricity bill. Respondents could choose higher rebates and lower ecosystem improvements or lower (or no) rebate and higher ecosystem amelioration. According to the experiment results, the highest total willingness to pay (WTP) is above € 144 per household and per year. Moreover, people's marginal WTP for a satisfactory fish stock reaches 250 €/year, that is three times the maximum rebate that was offered. Finally, all environmental attributes are considered as significant and worth a monetary effort. Therefore, hydroelectric concession bidders should give clear priority to environmental aspects.
    Keywords: Water Framework Directive, Choice Experiment, Hydropower
    Date: 2014–06–02
  2. By: Ignacio Lozano; Alexander Guarín
    Abstract: In this paper, we study the empirical relationship between credit funding sources and the financial vulnerability of the Colombian banking system. We propose a statistical model to measure and predict banking-fragility episodes associated with credit funding sources classified into retail deposits and wholesale funds. We compute the probability of financial fragility for both the aggregated banking system and the individual banks. Our approach performs a Bayesian averaging of estimated logit regression models with monthly balance sheet data between 1996 and 2013. The results show the increasing use of wholesale funding to support credit expansion is a potential source of financial fragility. Therefore, monitoring credit funding sources could provide an additional tool to warn against banking disruptions. Classification JEL: C11, C23, C52, C53, G01, G20, G21
    Date: 2014–03
  3. By: Lisa Bruttel
    Abstract: This paper presents results from an experiment on the effects of retail-price recommendations (RPRs) on consumer and retailer behavior. Despite their non-binding nature, RPRs may influence consumersÕ willingness to pay by setting a reference point. Loss averse consumers will then be reluctant to pay a price higher than the recommended one. Furthermore, at a given price level consumers will demand a larger quantity the higher the RPR is. We find evidence for both effects. They are stronger when the price recommendation contains information about the value of the product to the consumer instead of providing an uncorrelated anchor only. Retailers in this study react to RPRs in a similar way as consumers do, but they do not anticipate consumersÕ behavior well.
    Keywords: recommended retail price, consumer behavior, retailer behavior, experiment
    Date: 2014
  4. By: Boll, Christina; Leppin, Julian Sebastian; Schömann, Klaus
    Abstract: Overeducation is an often overlooked facet of untapped human resources. But who is overeducated and why? Relying on SOEP data 1984-2011, we use probit models for estimating the likelihood of entering overeducation and dynamic mixed multinomial logit models with random effects addressing state dependence and unobserved heterogeneity. As further robustness checks we use three specifications of the target variable, i.e. realized matches, self-assessment and twofold overeducation. We run separate analyses for men and women, East and West Germans and medium and highly educated persons. We find that overeducation is mainly state dependent. Nonetheless, even in the dynamic context staying employed proves to be risk-decreasing. By contrast, scars of past unemployment show up in a higher mismatch risk. Moreover, an employer change does not serve as a suitable exit strategy, and a dual qualification does not show up as a valid insurance against graduates' job mismatch. Overall, effects largely depend on the operationalization of overeducation. We conclude that to combat overeducation, focusing on continuous employment careers and circumventing unintentional withdrawals from the current job is crucial. Moreover, institutional impediments that restrain job match quality for certain groups (migrants, mothers) have to be tackled. -- Überqualifikation ist ein zuweilen übersehener Aspekt in der Debatte um ungenutzte Fachkräftepotenziale. Aber wer ist überqualifiziert, und warum? Basierend auf Daten des Sozio-oekonomischen Panels (SOEP) der Wellen 1984-2011 schätzen wir mit Probitmodellen die Wahrscheinlichkeit für neue Überqualifikation sowie mit dynamischen Multinomialen Mixed Logit-Modellen mit zufälligen Effekten die Wahrscheinlichkeit für Überqualifikation unter Berücksichtigung von Pfadabhängigkeit und unbeobachteter Populationsheterogenität. Das Messfehlerproblem kontrollieren wir durch drei verschiedene Spezifikationen der abhängigen Variable, die selbsteingeschätzte Überqualifikation, die statistische Überqualifikation (Realized Matches) sowie eine Kombination aus beidem. Wir führen die Schätzungen getrennt für Männer und Frauen, Ost- und Westdeutsche sowie Personen mittlerer und hoher Bildung durch. Unsere Analysen zeigen, dass Überqualifikation ein hohes Beharrungsvermögen hat. Allerdings vermindert Erwerbserfahrung das Risiko der Überqualifikation auch im dynamischen Modell unter Kontrolle unbeobachteter Heterogenität. Narbeneffekte früherer Arbeitslosigkeit hingegen zeigen sich in einem höheren Überqualifikationsrisiko. Weder ein Arbeitgeberwechsel noch (bei Akademiker/innen) eine Doppelqualifikation in Form von Lehre plus Studium taugen als wirksame Ausweichstrategien. Um Überqualifikation im Job zu vermindern, scheinen Strategien, die konti-nuierliche Erwerbskarrieren fördern, vielversprechend zu sein. Für bestimmte Gruppen am Arbeitsmarkt (Migranten, Mütter) erschweren zudem institutionelle Barrieren ein gutes Jobmatch, die es gezielt anzugehen gilt.
    Keywords: overeducation,dynamic mixed multinomial logit,probit model,mismatch,Germany,state dependence
    JEL: J24 C25 C33 J71
    Date: 2014

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.