nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2010‒03‒13
five papers chosen by
Philip Yu
Hong Kong University

  1. Measuring the Willingness to Pay to Avoid Guilt: Estimation using Equilibrium ad Stated Belief Models By Charles Bellemare; Alexander Sebald; Martin Strobel
  2. Preferences for Health Insurance in Germany and the Netherlands – A Tale of Two Countries By Peter Zweifel; Karolin Leukert; Stephanie Berner
  3. Improved Bid Prices for Choice-Based Network Revenue Management By Joern Meissner; Arne Strauss
  4. A Stochastic Frontier Model for Discrete Ordinal Outcomes: A Health Production Function By William Griffiths; Xiaohui Zhang; Xueyan Zhao
  5. Discriminatory fees, coordination and investment in shared ATM networks By Stijn Ferrari

  1. By: Charles Bellemare; Alexander Sebald; Martin Strobel
    Abstract: We estimate structural models of guilt aversion to measure the population level of willingness to pay (WTP) to avoid feeling guilt by letting down another player. We compare estimates of WTP under the assumption that higher-order beliefs are in equilibrium (i.e. consistent with the choice distribution) with models estimated using stated beliefs which relax the equilibrium requirement. We estimate WTP in the later case by allowing stated beliefs to be correlated with guilt aversion, thus controlling for a possible source of a consensus effect. All models are estimated using data from an experiment of proposal and response conducted with a large and representative sample of the Dutch population. Our range of estimates suggests that responders are willing to pay between 0.40 and 0.80 Euro to avoid letting down proposers by 1 Euro. Furthermore, we find that WTP estimated using stated beliefs is substantially overestimated (by a factor of two) when correlation between preferences and beliefs is not controlled for. Finally, we find no evidence that WTP is significantly related to the observable socio-economic characteristics of players.
    Keywords: Guilt aversion, Willingness to pay, Equilibrium and stated beliefs models
    JEL: C93 D63 D84
    Date: 2010
  2. By: Peter Zweifel (Socioeconomic Institute, University of Zurich); Karolin Leukert (Polynomics, Olten); Stephanie Berner (Polynomics, Olten)
    Abstract: This contribution contains an international comparison of preferences. Using two Discrete Choice Experiments (DCE), it measures willingness to pay for health insurance attributes in Germany and the Netherlands. Since the Dutch DCE was carried out right after the 2006 health reform, which made citizens explicitly choose a health insurance contract, two research questions naturally arise. First, are the preferences with regard to contract attributes (such as Managed-Care-type restrictions of physician choice) similar between the two countries? Second, was the information campaign launched by the Dutch government in the context of the reform effective in the sense of reducing status quo bias? Based on random-effects Probit estimates, these two questions can be answered as follows. First, while much the same attributes have positive and negative willingness to pay values in the two countries, their magnitudes differ, pointing to differences in preference structure. Second, status quo bias in the Netherlands is one-half of the German value, suggesting that Dutch consumers were indeed made to bear the cost of decision making associated with choice of a health insurance contract.
    Keywords: preference measurement, willingness to pay, health insurance, discrete-choice experiments, health reform, Germany, Netherlands
    JEL: C25 D12 I18
    Date: 2010–02
  3. By: Joern Meissner (Department of Management Science, Lancaster University Management School); Arne Strauss (Department of Management Science, Lancaster University Management School)
    Abstract: In many implemented network revenue management systems, a bid price control is being used. In this form of control, bid prices are attached to resources, and a product is offered if the revenue derived from it exceeds the sum of the bid prices of its consumed resources. This approach is appealing because once bid prices have been determined, it is fairly simple to derive the products that should be offered. Yet it is still unknown how well a bid price control actually performs. Recently, considerable progress has been made with network revenue management by incorporating customer purchase behavior via discrete choice models. However, the majority of authors have presented control policies for the booking process that are expressed in terms of which combination of products to offer at a given point in time and given resource inventories. The recommended combination of products as identified by these policies might not be representable through bid price control. If demand were independent from available product alternatives, an optimal choice of bid prices is to use the marginal value of capacity for each resource in the network. But under dependent demand, this is not necessarily the case. In fact, it seems that these bid prices are typically not restrictive enough and result in buy-down effects. We propose (1) a simple and fast heuristic that iteratively improves on an initial guess for the bid price vector; this first guess could be, for example, dynamic estimates of the marginal value of capacity. Moreover, (2) we demonstrate that using these dynamic marginal capacity values directly as bid prices can lead to significant revenue loss as compared to using our heuristic. Finally, (3) we investigate numerically how much revenue performance is lost due to the confinement of product combinations that can be represented by a bid price. Our heuristic is not restricted to a particular choice model and can be combined with any method that provides estimates of the marginal values of capacity. In our numerical experiments, we test the heuristic on some popular networks examples taken from peer literature. We use a multinomial logit choice model which allows customers from different segments to have products in common that they are considering purchasing. In most instances, our heuristic policy results in significant revenue gains over some currently available alternatives at low computational cost.
    Keywords: revenue management, network, bid prices, choice model
    JEL: C61
    Date: 2010–01
  4. By: William Griffiths; Xiaohui Zhang; Xueyan Zhao
    Abstract: The stochastic frontier model used for continuous dependent variables is extended to accommodate output measured as a discrete ordinal outcome variable. Conditional on the inefficiency error, the assumptions of the ordered probit model are adopted for the log of output. Bayesian estimation utilizing a Gibbs sampler with data augmentation is applied to a convenient re-parameterisation of the model. Using panel data from an Australian longitudinal survey, demographic and socioeconomic characteristics are specified as inputs to health production, whereas production efficiency is made dependent on lifestyle factors. Posterior summary statistics are obtained for selected health status probabilities, efficiencies, and marginal effects.
    Keywords: Bayesian estimation, Gibbs sampling, ordered probit, production efficiency
    JEL: C11 C21 C23 I12
    Date: 2010
  5. By: Stijn Ferrari (National Bank of Belgium, Financial Stability Department; Catholic University of Leuven)
    Abstract: This paper empirically examines the effects of discriminatory fees on ATM investment and welfare, and considers the role of coordination in ATM investment between banks. Our main findings are that foreign fees tend to reduce ATM availability and (consumer) welfare, whereas surcharges positively affect ATM availability and the different welfare components when the consumers' price elasticity is not too large. Second, an organization of the ATM market that contains some degree of coordination between the banks may be desirable from a welfare perspective. Finally, ATM availability is always higher when a social planner decides on discriminatory fees and ATM investment to maximize total welfare. This implies that there is underinvestment in ATMs, even in the presence of discriminatory fees
    Keywords: investment, coordination, ATMs, network industries, empirical entry models, spatial discrete choice demand models
    JEL: G21 L10 L50 L89
    Date: 2010–01

This nep-dcm issue is ©2010 by Philip Yu. 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.