nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2009‒06‒03
eight papers chosen by
Philip Yu
Hong Kong University

  1. Multilevel modeling of ordinal responses By Sophia Rabe-Hesketh
  2. In Silico Voting Experiments By Jean-François Laslier
  3. Defining environmental attributes as external costs in choice experiments: A discussion By Catalina M. Torres Figuerola; Antoni Riera Font
  4. Decision-making in General Practice: The importance of laboratory analyses when choosing medical actions By Fauli, Siri; Thue, Geir
  5. Price regulation and generic competition in the pharmaceutical market By Dalen, Dag Morten; Habeth, Tonje; Strøm, Steinar
  6. Decision-making in general practice - the effect of financial incentives on the use of laboratory analyses By Fauli Munkerud, Siri
  7. Wage Policies for Health Personnel - Essays on the Wage Impact on Hours of Work and Practice Choice By Sæther, Erik Magnus
  8. Innovation and market dynamics in the EPO market By Sorisio, Enrico; Strøm, Steinar

  1. By: Sophia Rabe-Hesketh (University of California–Berkeley)
    Abstract: Ordered categorical responses can be analyzed with different kinds of logistic regression models, the most popular being the cumulative logit or proportional odds model. Alternatively, ordinal probit models can be specified. When the data have a nested structure, with repeated observations for the same individual (as in longitudinal or panel data), or students nested in schools, these models can be extended by including random effects. I will describe the models and show how they can be estimated using gllamm. I will mention some elaborations of the models such as nonproportional odds and heteroskedastic errors. Finally, I will discuss how to obtain different types of predicted probabilities for these models to assess model fit, to visualize the model graphically, and to make inferences for individual units.
    Date: 2009–06–05
  2. By: Jean-François Laslier (Department of Economics, Ecole Polytechnique - CNRS : UMR7176 - Polytechnique - X)
    Abstract: This paper presents computer simulations of voting rules: Plurality rule, Approval voting and the Copeland and Borda rules, with voters voting sincerly or strategically. Different ways of generating random preference profiles are introduced: Rousseauist cultures are suitable for common interest project assessment; Impartial cultures are standard in Social Choice Theory; Distributive cultures and Spatial Euclidean ones are standard in Political Science.
    Keywords: Social Choice. Voting Rules. Impartial Culture. Condorcet. Borda
    Date: 2009–06–02
  3. By: Catalina M. Torres Figuerola (Centre de Recerca Econòmica (UIB · Sa Nostra)); Antoni Riera Font (Centre de Recerca Econòmica (UIB · Sa Nostra))
    Abstract: After doing a CE literature review to examine the dominant trends around the definition of environmental attributes in terms of their identification as external benefits or costs, their description through qualitative or quantitative attribute level labels, their number of levels and their assumed relationship with utility (i.e. linear vs non-linear), three main conclusions have been drawn. First, definition of environmental attributes as external costs has been uncommon. Second, only one single parameter has been estimated for most of them, in which cases the number of quantitative and qualitative attributes has been similar. Third, nonlinear effects have been mainly depicted through use of qualitative attributes. In this context, this paper examines the policy relevance of defining the environmental attributes as external costs when the assessment of welfare losses induced by potential impacts from polluting activities is the issue. It shows how a cost-based attribute definition allows identifying the environmental attributes through impact pathway analyses not only enabling links between welfare estimates and actual impact magnitudes but also promoting the description of attribute levels in quantitative terms.
    Keywords: Choice experiments, environmental attributes, utility specification, external costs, impact pathway, eutrophication
    Date: 2009
  4. By: Fauli, Siri (The Norwegian Medical Association, The Norwegian Quality Improvement of); Thue, Geir (The Norwegian Quality Improvement of Laboratory Services in Primary Care)
    Abstract: The focus of this study is the effect of a laboratory analysis and socioeconomic variables on choosing medical actions in a specific situation (a clinical vignette - a young woman, Mrs Hansen, with dyspepsia - presented to GPs). We assume that the GP’s decision depends on what he or she thinks is best for the patients, based on the best clinical evidence available. Significant variables associated with the choice of medical actions are: the result of the Helicobacter pylori (HP) test, the GP’s stated importance of HPRT, the location of the general practice, the GP recommending sick leave, the GP’s stated probability that Mrs Hansen’s symptoms are due to a H.pylori infection after the HP-result is known, and how the GP follows up the patient. Our results show that the HP-analysis has a significant and major influence on the GPs choice of medical actions. Therefore the quality of the analysis is likely to affect the patients’ health and social costs. Hence institutions for quality monitoring and improvement are important elements of health care reforms. Such institutions should balance cost and benefits of quality improving measures, and will be the focus of closer studies in our future research.
    Keywords: Discrete choice models; Decision-making; Primary Health Care
    JEL: I12
    Date: 2009–06–07
  5. By: Dalen, Dag Morten (Handelshøyskolen BI); Habeth, Tonje (Handelshøyskolen BI); Strøm, Steinar (Department of Economics, University of Oslo)
    Abstract: In March 2003 the Norwegian government implemented yardstick based price regulation schemes on a selection of drugs experiencing generic competition. The retail price cap, termed “index price”, on a drug (chemical substance) was set equal to the average of the three lowest producer prices on that drug, plus a fixed wholesale and retail margin. This is supposed to lower barriers of entry for generic drugs and to trigger price competition. Using monthly data over the period 1998-2004 for the 6 drugs (chemical entities) included in the index price system, we estimate a structural model enabling us to examine the impact of the reform on both demand and market power. Our results suggest that the index price helped to increase the market shares of generic drugs and succeeded in triggering price competition.
    Keywords: Discrete choice; demand for pharmaceuticals; monopolistic competition; evaluation of yardstick based price regulation
    JEL: C35 D43 I18 L11
    Date: 2009–06–04
  6. By: Fauli Munkerud, Siri (Norwegian Quality Improvement of Laboratory Services in Primary Care (NOKLUS))
    Abstract: This paper examines the reaction of general practitioners (GPs) to a reform in 2004 in the remuneration system for using laboratory services in general practice. Data from Norway make it possible to distinguish between income motivation and service motivation. The purpose of this paper is to study whether income motivation exists, and if so, the degree of income motivation among general practitioners (GPs) in Norway regarding the use of laboratory services in general practices. We argue that the degree of income motivation among GPs is stronger when the physicians are uncertain about the utility of the laboratory service in question. We have panel data from actual physician-patient encounters in general practices in the years 2001-2004, and use discrete choice analysis and random effects models. Our results indicate that there may be an income motivation among GPs regarding using laboratory services as, after the reform, the GPs chose to use laboratory services less frequently where the fees had been most reduced. In addition, estimation results show that an increase in the fees will lead to a small but significant increase in use. The reform led to minor changes in the use of laboratory analyses in GPs’ offices, and we argue that financial incentives were diluted because they were in conflict with medical recommendations and existing medical practice. The patient’s age has the most influence on GPs’ choice regarding use of laboratory services. The results support the hypothesis that the impact of income increases with increasing uncertainty about diagnosis and treatment. The policy implication of our results is that financial incentives alone are not an effective tool for influencing the use of laboratory services in GPs’ offices.
    Keywords: Financial incentives; laboratory analyses; diagnostic uncertainty; medical practice.
    JEL: I10
    Date: 2009–06–02
  7. By: Sæther, Erik Magnus (Ragnar Frisch Centre for Economic Research)
    Abstract: This thesis aims to explore the short-term impact of increased wages on the working hours of health personnel and their practice choice. An additional objective is to identify existing compensating differentials in the job market for health personnel.
    Keywords: physicians; registered nurses; discrete choice; non-convex budget sets; labor supply; sector-specific wages
    JEL: C25 I10 J22
    Date: 2009–06–07
  8. By: Sorisio, Enrico (PharmaNess scarl; University of Turin); Strøm, Steinar (University of Oslo; The Frisch Centre, Oslo; University of Turin)
    Abstract: In this paper we study the demand and supply of erythropoietin in four Nordic countries, using an econometric model based on discrete choice and a random utility model. It measures the effect of price changes as well as the loyalty of patients and physicians to a drug. Our main aims are to estimate demand for EPO and to determine the degree of competition in this Nordic market. The main motivation for this paper is to analyze the impact of product innovation on market power and welfare, e.g. on consumer and producer surplus. The product innovation is the entry of Aranesp in the Nordic market.
    Keywords: Discrete choice; demand for pharmaceuticals; monopolistic competition; EPO
    JEL: C35 D43 I18 L11
    Date: 2009–06–04

This nep-dcm issue is ©2009 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.