nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2008‒01‒12
four papers chosen by
Philip Yu
Hong Kong University

  1. Reference-Dependent Preferences and Loss Aversion: A Discrete Choice Experiment in the Health-Care Sector By Einat Neuman; Shoshana Neuman
  2. Religion, Terrorism and Public Goods: Testing the Club Model By Eli Berman; David D. Laitin
  3. How Costly Is Hospital Quality? A Revealed-Preference Approach By John A. Romley; Dana Goldman
  4. The Bayesian Additive Classification Tree Applied to Credit Risk Modelling By Junni L. Zhang; Wolfgang Härdle

  1. By: Einat Neuman (University Center of Ariel); Shoshana Neuman (Bar-Ilan University, CEPR and IZA)
    Abstract: A Discrete Choice Experiment (DCE) in the health-care sector is used to test the loss aversion theory that is derived from reference-dependent preferences: The absolute subjective value of a deviation from a reference point is generally greater when the deviation represents a loss than when the same-sized change is perceived as a gain. As far as is known, this paper is the first to use a DCE to test the loss aversion theory. A DCE appears to be a highly suitable tool for this testing because it estimates the marginal valuations of attributes, based on deviations from a reference point (a constant scenario). Moreover, loss aversion can be examined for each attribute separately. A DCE can also be applied to nontraded goods with non-tangible attributes. A health-care event is used for empirical illustration: The loss aversion theory is tested within the context of preference structures for maternity-ward attributes, estimated using data entailing 3850 observations from a sample of 542 women who recently gave birth. Seven hypotheses are presented and tested. Overall, significant support for behavioral loss aversion theories was found.
    Keywords: preferences, attributes, loss aversion, reference-dependence, Discrete Choice Experiment, maternity-wards
    JEL: D01 D12 I19
    Date: 2007–12
  2. By: Eli Berman; David D. Laitin
    Abstract: Can rational choice modeling explain why Hamas, Taliban, Hezbollah and other radical religious rebels are so lethal? The literature rejects theological explanations. We propose a club framework, which emphasizes the function of voluntary religious organizations as efficient providers of local public goods in the absence of government provision. The sacrifices religious clubs require are economically efficient (Iannaccone (1992)), making them well suited for solving the extreme principal-agent problems faced by terrorist and insurgent organizations. Thus religious clubs can be potent terrorists. That explanation is supported by data on terrorist lethality in the Middle East. The same approach explains why religious clubs often choose suicide attacks. Using three data sources spanning a half century, and comparing suicide attackers to civil war insurgents, we show that suicide attacks are chosen when targets are "hard," i.e., difficult to destroy. Data from Israel/Palestine confirm that prediction. To explain why radical religious clubs specialize in suicide attacks we model the choice of tactics by rebels attacking hard targets, considering the human costs and tactical benefits of suicide attacks. We ask what a suicide attacker would have to believe to be rational. We then embed that attacker and other operatives in a club model. The model has testable implications for tactic choice and damage achieved by clubs and other rebels, which are supported by data on terrorist attacks in the Middle East: Radical religious clubs are more lethal and choose suicide terrorism more often, when they provide benign local public goods. Our results suggest benign tactics to counter terrorism by religious radicals.
    JEL: D2 D31 H41 H56 H68 J0 J13 O17 O24 Z12
    Date: 2008–01
  3. By: John A. Romley; Dana Goldman
    Abstract: One of the most important and vexing issues in health care concerns the cost to improve quality. Unfortunately, quality is difficult to measure and potentially confounded with productivity. Rather than relying on clinical or process measures, we infer quality at hospitals in greater Los Angeles from the revealed preference of pneumonia patients. We then decompose the joint contribution of quality and unobserved productivity to hospital costs, relying on heterogeneous tastes among patients for plausibly exogenous quality variation. We find that more productive hospitals provide higher quality, demonstrating that the cost of quality improvement is substantially understated by methods that do not take into account productivity differences. After accounting for these differences, we find that a quality improvement from the 25th percentile to the 75th percentile would increase costs at the average hospital by nearly fifty percent. Improvements in traditional metrics of hospital quality such as risk-adjusted mortality are more modest, indicating that other factors such as amenities are an important driver of both hospital costs and patient choices.
    JEL: D24 I11
    Date: 2008–01
  4. By: Junni L. Zhang; Wolfgang Härdle
    Abstract: We propose a new nonlinear classification method based on a Bayesian "sum-of-trees" model, the Bayesian Additive Classification Tree (BACT), which extends the Bayesian Additive Regression Tree (BART) method into the classi- fication context. Like BART, the BACT is a Bayesian nonparametric additive model specified by a prior and a likelihood in which the additive components are trees, and it is fitted by an iterative MCMC algorithm. Each of the trees learns a different part of the underlying function relating the dependent variable to the input variables, but the sum of the trees offers a flexible and robust model. Through several benchmark examples, we show that the BACT has excellent performance. We apply the BACT technique to classify whether firms would be insolvent. This practical example is very important for banks to construct their risk profile and operate successfully. We use the German Creditreform database and classify the solvency status of German firms based on financial statement information. We show that the BACT outperforms the logit model, CART and the Support Vector Machine in identifying insolvent Firms.
    Keywords: Classi¯cation and Regression Tree, Financial Ratio, Misclassification Rate, Accuracy Ratio
    JEL: C14 C11 C45 C01
    Date: 2008–01

This nep-dcm issue is ©2008 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.