nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2015‒05‒02
eight papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  3. Testing for Complementarity: Glyphosate Tolerant Soybeans and Conservation Tillage By Edward Perry; GianCarlo Moschini; David A. Hennessy
  4. Automobile Demand and Supply in Brazil: Effects of Tax Rebates and Trade Liberalization on Price-marginal Cost Markups in the 1990s By Eduardo P. S. Fiuza
  5. La pêche professionnelle est-elle un facteur d’attractivité récréative sur le littoral ? By Carole Ropars-Collet; Mélody Leplat; Philippe Le Goffe; Marie Lesueur
  6. Multinational versus national firms on capital adjustment costs: A structural approach By Lapatinas, Athanasios
  7. Individuals’ behaviour with respect to parking alternatives: a laboratory experiment By Bergantino, Angela Stefania; De Carlo, Angela; Morone, Andrea
  8. Is innovation activity persistent among small firms in developing countries? Evidence from Vietnam By Trinh, Long

  1. By: Valerio Gatta (University of Roma Tre and CREI); Edoardo Marcucci (University of Roma Tre and CREI)
    Abstract: This paper derives policy implications concerning a specifically developed questionnaire administration procedure aimed at eliciting agent-s pecific preferences for alternative policy variables with respect to the implementation of pol icy changes in the case of urban freight transport. In particular the research, based on the case of Rome’s Limited Traffic Zone, discusses alternative policy implementations whose impact can be tested ex-ante given the elicitation method adopted. After describing attribute definition and selection, questionnaire administration, data collection and treatment, will ingness to pay estimates are calculated. The paper tests, from a policy-maker’s perspective, the implications deriving from the presence of inter-agent heterogeneity and the specific composition of an improving and equally impacting policy on all agent-types’ utility. The paper shows how an agent-specific approach might increase decision makers’ awareness and help them taking better decisions.
    Keywords: urban freight policy, agent-type heterogeneity, ex-ante reactions, stated preferences, discrete choice modelling, and willingness to pay
    Date: 2014
  2. By: Valerio Gatta (University of Roma Tre and CREI); Edoardo Marcucci (University of Roma Tre and CREI); Luisa Scaccia (University of Macerata)
    Abstract: This paper systematically compares methods to build confidence intervals for willingness to pay measures in a discrete choice context. It contributes to the literature by including methods developed in other research fields. Monte Carlo simulations are used to assess the performance of all the methods considered. The various scenarios evaluated reveal a certain skewness in the estimated willingness to pay distribution. This should be reected in the condence intervals. Results show that the commonly used Delta method, producing symmetric intervals around the point estimate, often fails to account for such a skewness. Both the Fieller method and the likelihood ratio test inversion method produce more realistic confidence intervals. Some bootstrap methods also perform reasonably well. Finally, empirical data are used to illustrate an application of the methods considered.
    Keywords: Confidence intervals, willingness to pay, discrete choice models, elasticities, standard errors
    Date: 2014
  3. By: Edward Perry; GianCarlo Moschini (Center for Agricultural and Rural Development (CARD)); David A. Hennessy (Center for Agricultural and Rural Development (CARD))
    Abstract: Many decisions in agriculture are made over combinations of inputs and/or practices that may be complements. The presence of complementarity among producer decisions can have deep implications for market outcomes and for the effectiveness of policies intended to influence them. Identifying complementarity relations, however, is a challenging pursuit. Drawing on recent methodological advances, in this paper we propose a new test for complementarity between glyphosate tolerant soybeans and conservation tillage that overcomes limitations of previous studies. Specifically, we develop a structural discrete choice framework of joint soybean-tillage adoption that explicitly models both complementarity and unobserved heterogeneity. The model is estimated with a large dataset of farm-level choices that spans the 1998–2011 period and contains repeated observations for many of the sampled individuals. We find that glyphosate tolerant soybeans and conservation tillage are indeed complementary practices, a conclusion supported by several robustness checks. In addition, our estimation shows that farm operation scale promotes the adoption of both conservation tillage and glyphosate tolerant seed, and that all of higher fuel prices, more droughty conditions, and soil erodibility increase use of conservation tillage. We also apply our results to simulate annual adoption rates for conservation tillage in a scenario without glyphosate tolerant soybeans available as a choice. We find that the adoption of conservation tillage has been about ten percent higher due to the advent of glyphosate tolerant soybeans. Key Words: complementarity, conservation tillage, discrete choice models, genetically engineered crops, mixed multinomial logit, supermodularity, technology adoption, unobserved heterogeneity. JEL codes: C35, D22, Q12, Q55
    Date: 2015–04
  4. By: Eduardo P. S. Fiuza
    Abstract: This work is a pioneer effort to estimate supply and demand of automobiles in Brazil with a Discrete Choice model in a differentiated product oligopolistic market. We apply a Nested Logit model to the demand side and assume differentiated product price-setting firms on the supply side to evaluate the severe transformations undergone by the Brazilian automobile industry in the 1990s, especially policy events such as the tax rebates created for the so-called popular models (introduced in 1993) and the trade liberalization (initiated in 1991 and partially reversed in 1995 under the so-called Automotive Regime). We find that, although domestic cars still enjoyed considerably higher price-marginal cost markup rates than their imported counterparts (net of VATs and duties) in all market segments at the end of our sample (1997), these rates had dropped drastically and permanently during the 1995 import boom, not only because of import, but also from fiercer domestic competition. A perhaps striking finding is that, as opposed to what was verified in studies for other countries, popular and compacts enjoy the highest price-marginal cost markup rates, as they are significantly less threatened by imported competitors than the larger and luxurious models. These rates do not translate into higher pricecost margins in money units, but due to their high sales volumes these models account for great shares of the firms’ profits. Este trabalho é um esforço pioneiro para a estimação da oferta e da demanda de automóveis no Brasil com um modelo de Escolha Discreta em um mercado oligopolístico com produtos diferenciados. Nós aplicamos uma modelagem econométrica de logit hierárquico (Nested Logit) para o lado da demanda, e adotamos a hipótese de firmas fixadoras de preços com múltiplos produtos diferenciados no lado da oferta, para avaliar as profundas transformações ocorridas na indústria automotiva brasileira nos anos 1990, especialmente a adoção de políticas como os incentivos fiscais para os chamados carros populares (introduzidos em 1993) e a liberalização comercial (iniciada em 1991 e revertida parcialmente sob o chamado regime automotivo). Nós constatamos que, embora os carros nacionais ainda auferissem taxas consideravelmente altas de markup em relação aos seus similares importados (líquidas de impostos sobre valor agregado e tarifas) em todos os segmentos de mercado no final da nossa amostra (1997), essas taxas tiveram uma queda drástica e permanente durante o boom de importações de 1995, não apenas por causa dessas importações, mas também em virtude da competição doméstica mais acirrada. Uma constatação, talvez surpreendente, é que, ao contrário do verificado em estudos em outros países, os carros populares e compactos têm as maiores taxas de markup, na medida em que são muito menos ameaçados pela competição estrangeira do que os carros grandes e de luxo. Essas taxas não se traduzem em margens preçocusto mais altas também em unidades monetárias, mas, devido ao grande volume de vendas, esses modelos correspondem a grandes percentagens dos lucros das firmas.
    Date: 2015–01
  5. By: Carole Ropars-Collet; Mélody Leplat; Philippe Le Goffe; Marie Lesueur
    Abstract: The concept of multifunctionality of fishing activities is emerging, as fishery activities do not only provide commodity goods but have others functions (environmental, social, territorial, etc.). We choose to focus on the provision of amenities, such as the presence of fishing boats or direct sales of seafood, for which there is a demand that partly conditions the individual choices of visit on the coastline. We used choice experiments to estimate willingness to pay for these amenities produced jointly by commercial fishing. The empirical study was conducted on a sample of one thousand people we surveyed along the coasts of French Channel and of the North Sea.
    Keywords: Multifunctional fishery, Non-market value, Choice experiments
    JEL: C35 C9 Q22 Q26
    Date: 2015
  6. By: Lapatinas, Athanasios
    Abstract: This paper provides a different perspective on the firm-level empirical analysis of the relation between foreign ownership and capital demand adjustment in host countries. The author estimates a dynamic structural model of investment on a sample of 4672 Belgian firms observed between 2003 and 2010 that permits to distinguish the 'ownership status' of firms. He considers a dynamic discrete choice model of a general specification of adjustment costs including convex and nonconvex components. He uses the method of simulated moments procedure to estimate the structural parameters. The results indicate that multinational's affiliates face lower capital adjustment costs than national firms.
    Keywords: Multinational Firms,Investment,Capital Adjustment Costs
    JEL: F23 D24 D92 G31
    Date: 2015
  7. By: Bergantino, Angela Stefania; De Carlo, Angela; Morone, Andrea
    Abstract: The aim of this paper is to analyse the trade-off between parking space availability and cost, in terms of time saving. This information is pivotal when designing parking policies in terms of fares, investments and regulation. A relevant body of literature has focused on parking behaviour (e.g. travellers’ choice of parking type and location). However, little attention has been devoted to understand how risk and uncertainty influence drivers’ behaviours in parking decision. This paper address the parking choice problem by means of a laboratory experiments, which aims to collect disaggregate data on travellers’ responses to changes in parking attributes and related information. Different components of the parking activity (e.g., general in-vehicle time, parking search time, egress time) are controlled for, in relation to the characteristics of the respondent. In order to avoid heterogeneity in relation to journey purposes we focus on individuals’ mobility. The collected data is used to build simple model of consumer’s choice related to parking decision, taking explicitly into consideration both risk and uncertainty.
    Keywords: parking; risk; uncertainty; choice behaviour; laboratory
    JEL: C9 C91 R4 R41
    Date: 2015
  8. By: Trinh, Long
    Abstract: Using firm-level panel data collected in Vietnam bi-annually from 2005 to 2013, this paper examines whether innovation is persistent among small firms in Vietnam. The empirical results obtained from dynamic random effect probit and dynamic random effect ordered probit show that the innovation activity is persistent among these small firms. Our estimation results also show slightly different roles of human capital of firm’s owner and employees in innovation activities. While the owner’s human capital is associated with creating a new product, employees’ human capital is positively correlated with upgrading the existing products or production procedure. However, we do not find evidence on the roles of unobserved heterogeneity in explaining this persistence. Our results are consistent with results found in the literature for firms in developed economies.
    Keywords: Innovation, Persistence of Innovation, Unobserved heterogeneity, Dynamic Random Effect Probit Model, Dynamic Random Effect Ordered Probit Model, Small and Medium Enterprises, Vietnam
    JEL: C23 C25 L20 O31 O33
    Date: 2015–04–14

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.