nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2016‒09‒25
five papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. Generalized Indirect Inference for Discrete Choice Models By Marianne Bruins; James A. Duffy; Michael P. Keane; Anthony A. Smith, Jr
  2. An empirical analysis of consumers' concerns about privacy through using the internet By Koguchi, Teppei; Kuroda, Toshifumi; Ida, Takanori
  3. Willingness to pay for cloud computing service of SMEs in Thailand By Srinuan, Chalita
  4. Efficiency-Morality Trade-Offs in Repugnant Transactions: A Choice Experiment By Elias, Julio; Lacetera, Nicola; Macis, Mario
  5. The impact of asymmetric regulation on product bundling: The case of fixed broadband and mobile communications in Japan By Kuroda, Toshifumi; Ida, Takanori; Koguchi, Teppei

  1. By: Marianne Bruins (Nuffield College and Dept of Economics, Univesity of Oxford); James A. Duffy (Nuffield College, Dept of Economics and Institute for New Economic Thinking at the Oxford Martin School, Univesity of Oxford); Michael P. Keane (Nuffield College and Dept of Economics, Univesity of Oxford); Anthony A. Smith, Jr (Yale University)
    Abstract: This paper develops and implements a practical simulation-based method for estimating dynamic discrete choice models. The method, which can accommodate lagged dependent variables, serially correlated errors, unobserved variables, and many alternatives, builds on the ideas of indirect inference. The main difficulty in implementing indirect inference in discrete choice models is that the objective surface is a step function, rendering gradientbased optimization methods useless. To overcome this obstacle, this paper shows how to smooth the objective surface. The key idea is to use a smoothed function of the latent utilities as the dependent variable in the auxiliary model. As the smoothing parameter goes to zero, this function delivers the discrete choice implied by the latent utilities, thereby guaranteeing consistency. We establish conditions on the smoothing such that our estimator enjoys the same limiting distribution as the indirect inference estimator, while at the same time ensuring that the smoothing facilitates the convergence of gradient-based optimization methods. A set of Monte Carlo experiments shows that the method is fast, robust, and nearly as efficient as maximum likelihood when the auxiliary model is sufficiently rich.
    Date: 2015–07–15
  2. By: Koguchi, Teppei; Kuroda, Toshifumi; Ida, Takanori
    Abstract: In this research, an empirical analysis based on a questionnaire survey was carried out on these sorts of factors on the user side, and the effects that individual attributes and usage conditions have on concerns about privacy and on awareness and understanding of privacy policies were clarified. In this research, specifically we attempt to analyze the kinds of effects that "individual attributes and service-usage characteristics" have on "concerns about individual privacy and the understanding of privacy policies." Therefore, we established a model with the former as the dependent variables and the latter as the explanatory variables and carried out the estimates. For the estimates, we used data from a Web questionnaire survey with a sample size of about 2,000, and used a binary logit model and ordered logit model to identify the factors that affect concerns about individual privacy and understanding of privacy policies.
    Date: 2015
  3. By: Srinuan, Chalita
    Abstract: The great promise of cloud computing is the immediate access to enterprise grade software and next generation Information Technology solutions. Cloud service enables SMEs anywhere to expand their market reach, delivery and service, and customer interaction. Some small and medium enterprises (SMEs) are yet to fully realize the advantages of cloud solutions. In the meantime, hundreds of cloud vendors are preparing for the expected major upswing in popularity among cloud services for SMEs and for private consumers. This study examines the factor affecting a decision to use cloud computing service for Thai SMEs. A questionnaire was employed for data collection from a sample of SMEs that use cloud computing technology in the Bangkok area during January 2015- June 2015. A statistic model was utilized in order to analyses the determined factor on using cloud computing service of Thai SMEs. Moreover, the willingness-to-pay (WTP) to additional cloud computing service was calculated. The findings can be used to gauge SMEs demand for improved cloud computing services.
    Keywords: Willingness to pay,cloud service,SMEs
    Date: 2015
  4. By: Elias, Julio (Universidad del CEMA); Lacetera, Nicola (University of Toronto); Macis, Mario (Johns Hopkins University)
    Abstract: Societies prohibit many transactions considered morally repugnant, although potentially efficiency-enhancing. We conducted an online choice experiment to characterize preferences for the morality and efficiency of payments to kidney donors. Preferences were heterogeneous, ranging from deontological to strongly consequentialist; the median respondent would support payments by a public agency if they increased the annual kidney supply by six percentage points, and private transactions for a thirty percentage-point increase. Fairness concerns drive this difference. Our findings suggest that cost-benefit considerations affect the acceptance of morally controversial transactions, and imply that trial studies of the effects of payments would inform the public debate.
    Keywords: repugnant transactions, efficiency, morality, markets, preferences
    JEL: C91 D01 D63 D64 I11
    Date: 2016–09
  5. By: Kuroda, Toshifumi; Ida, Takanori; Koguchi, Teppei
    Abstract: Product bundling may benefit or harm consumers dependingon the correlation betweenconsumer willingness to pay for the bundledgoods and the levels of market dominance of firms. We develop astructural demand model that allows for correlatedconsumer's willingness to pay and flexible complementarities/substitutabilities. We estimate thismodel using data fromthree surveys conducted bythe JapanMinistry of Internal Affairs and Communications. The estimation results show that fixed broadband and mobile communications are complements for theJapanese telecommunication incumbentbut ambiguousfor competitors. To assess the effect of asymmetric regulation on product bundling by the incumbent, we conduct a counterfactual analysis of a two-stage game where firms choose whether to set bundle discount or not to set for fixed-broadband and mobile communications at stage one and set prices at stage two. The subgame perfect Nash equilibrium ofthetwo-stage game with/without asymmetric regulation shows that mixed-bundling is the dominant strategy for the incumbent. To avoid cannibalization, the incumbent set large discounts for bundle and set high prices for separate goods. Along with high market dominance of the incumbent, this strategy decreases the consumer surplus by 18.8%. Under subgame perfect Nash equilibrium, thediffusion ratesof fixed broadband decreases from 88.9% to 88.0% andthe diffusion rates of mobile communications increases from 95.25 to 95.71%.We also find that pure bundling,asa toolfor leverage,is not a subgame perfect Nash equilibrium.
    Keywords: Fixed-to-mobile substitution,Bundles,Leverage,Discrete-Choice Model
    JEL: L96 D43
    Date: 2015

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.