nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2007‒01‒14
thirteen papers chosen by
Philip Yu
Hong Kong University

  1. Countries, Regions and Multinational Firms: Location Determinants in the European Union By Rodrigo Alegria
  2. An Analysis of Gender Differences in UK Graduate Migration Behaviour By Alessandra Faggian; Stephen Sheppard; Philip Mccann
  3. Where Art Thou? Regional Distribution of Culture Workers in Finland By Riikka Penttinen
  4. Using Expert Judgment to Assess Adaptive Capacity to Climate Change: Evidence From a Conjoint Choice Survey By Anna Alberini; Aline Chiabai
  5. Tourists’ Satisfaction Vs. Residents’ Quality of Life in Medium Sized European Cities: A Conjoint Analysis Approach for Cultural Tourism’s Impact Assessment By Patrizia Riganti
  6. Economic Analysis of On-Line Music: Choice Between On-Line and Traditional Music Shops By Toshiaki Takita
  7. Modeling collective rationality: a nonparametric test on experimental data By Sabrina Buyneel; Laurens Cherchye; Bram De Rock
  8. Alterung und technologisches Innovationspotential : Eine Linked-Employer-Employee-Analyse By Lutz Schneider
  11. An econometric specification of monetary policy dark art By Ielpo, Florian; Guégan, Dominique
  12. Observational Learning in the Motion Picture Market By Santugini, Marc
  13. “Aggregating judgments by the majority method” By García-Bermejo, Juan Carlos

  1. By: Rodrigo Alegria
    Abstract: European economic integration and its enlargement phases foster the flows of international investments. This explains why the spatial distribution of economic activity is to an increasing extent determined by the location decisions of multinational firms (MNEs). Therefore, from a regional economy perspective, the geography of multinational activity is a policy concern for regional and local authorities. Not only does foreign activity have several contributions and implications for the regional economic development but also understanding the location process of these economic activities is crucial for adequate policy responses. This paper analyses the location decisions of European multinational firms across European countries (25) and regions (NUTS2). An emphasis is placed on whether location determinants for MNEs either change, or if not, which one dominates, at different spatial levels. We expect to find that agglomeration and dispersion forces behave in a different fashion depending on whether country or regional geographical scales are taken into consideration. We seek to explain how economic integration causes some multinational activity to locate in peripheral countries meaning a dispersion process at a supranational scale. The experience of Spain and Portugal in 1986, and more recently CEE countries, confirms this. They have received huge amounts of FDI coming from European countries. However, when the location decision is considered within a country, agglomeration tendencies come to dominate. The regions more developed within the host country attract the majority of these foreign inflows. With the recently incorporation of the knowledge capital model into a New Economic Geography (NEG) setting the links between multinational production and agglomeration are theoretically considered. But NEG setting seems to be scale independent. The same framework is used for analysing regional, urban and international issues. Then, an empirical test is necessary in order to account for these geographical scale differences. Empirically, we use a range of discrete choice models for location choices of MNEs across Europe. The independent variables are grouped into four categories: market access, labour market, agglomeration and others. The first results seem to confirm our hypothesis of a different behaviour of the location determinants depending on the geographical scale taken into consideration.
    Date: 2006–08
  2. By: Alessandra Faggian; Stephen Sheppard; Philip Mccann
    Abstract: In this paper we employ dichotomous, multinomial and conditional logit models in order to analyse the employment-migration behaviour of some 300,000 UK university graduates. By controlling for a range of variables related to human-capital acquisition and local economic conditions, we are able to distinguish between different types of sequential migration behaviour from domicile to higher education and on to employment. Our findings indicate that UK female graduates are generally more migratory than male graduates. We suggest that the explanation for this result lies in the fact that migration can be used as a partial compensation mechanism for gender bias in the labour market.
    Date: 2006–08
  3. By: Riikka Penttinen
    Abstract: This study seeks to shed light on the regional distribution of culture workers in Finland. What factors – if any - make the location decisions of culture workers different from that of others? This study uses a rich micro level data for an application of multinomial logit model. The data is from the Finnish Longitudinal Census File and it contains information e.g. on individual's personal charactersitics, family characteristics and working life characteristics. The estimation results show that being a culture worker is an important factor in locational choice: the coefficient of living in a metropolitan area compared to rural areas is highly positive. According to the estimated marginal effects, the likelihood of living in a metropolitan region increases as much as 22 percentage points if the person is a culture worker. Another interesting notion is that the residential choices of cultural entrepreneurs seem to differ from that of other entrepreneurs.
    Date: 2006–08
  4. By: Anna Alberini; Aline Chiabai
    Abstract: We use conjoint choice questions to ask public health and climate change experts, contacted at professional meetings in 2003 and 2004, which of two hypothetical countries, A or B, they deem to have the higher adaptive capacity to certain effects of climate change on human health. These hypothetical countries are described by a vector of seven attributes, including per capita income, inequality in the distribution of income, measures of the health status of the population, the health care system, and access to information. Probit models indicate that our respondents regard per capita income, inequality in the distribution of income, universal health care coverage, and high access to information as important determinants of adaptive capacity. A universal-coverage health care system and a high level of access to information are judged to be equivalent to $12,000-$14,000 in per capita income. We use the estimated coefficients and country sociodemographics to construct an index of adaptive capacity for several countries. In panel-data regressions, this index is a good predictor of mortality in climatic disasters, even after controlling for other determinants of sensitivity and exposure, and for per capita income. We conclude that our conjoint choice questions provide a novel and promising approach to eliciting expert judgments in the climate change arena.
    Date: 2006–08
  5. By: Patrizia Riganti
    Abstract: This paper discusses the use of conjoint analysis to assess the non market impacts of tourism presence in small and medium sized European cities. It presents the methodological approach developed to this purpose within the EU funded project PICTURE (Pro-active management of the Impact of Cultural Tourism upon Urban Resources and Economies) and its application to the case of the city of Syracuse, Italy. Tourism is one of Europe’s largest economic sectors and features among the largest key industries of the 21st century and cultural tourism is one of the forms of tourism that is expected to witness the most important growth in the future. Sustainable cultural tourism strategies have the potential to assist the conservation of local identities, embedded in their respective cultural heritage, while supporting economic growth. However, tourism in cultural sites can also bring negative impacts, which need to be analyzed and assessed. Economic valuation can support decision making in this sector. This paper first discusses to what extent is possible to value in economic terms the positive and negative externalities brought by cultural tourism to heritage destinations, and which are the currently available valuation techniques. Then it focuses on how to manage destinations in a way to limit negative impacts whilst spreading the positive ones in the region. Then it reports the results of a conjoint analysis study on the city of Syracuse, Italy, carried out on a sample of residents and tourists. In particular it looks at the marginal utility associated to attributes interpreting the carrying capacity of the site. Finally, the paper focuses on the potential and limitations of conjoint analysis studies for the above purposes. Conjoint analysis is a non market valuation technique frequently used to place a value on a good. It is a stated-preference method, in the sense that it asks individuals what they would do under hypothetical circumstances, rather than observing actual behaviors on marketplaces, simulating a hypothetical market and analysing stated preferences rather than observing actual market behaviour. In a typical conjoint analysis choice individuals are asked to choose among alternative variants of a good described by a number of attributes. The alternatives differ from one another in the levels taken by two or more of the attributes. The technique assumes the choice between the alternatives is driven by the respondent’s underlying utility. Conjoint choice experiments were initially developed by Louviere and Hensher (1982) and Louviere and Woodworth (1983). Conjoint choice experiments have been widely used to value environmental and natural resources, and more recently cultural heritage. Previous research seems to confirm that the technique is flexible enough and can be successfully adapted to the assessment of policy strategies. The paper discusses the steps that should be considered when developing a conjoint choice experiment for similar purposes.
    Date: 2006–08
  6. By: Toshiaki Takita
    Abstract: The aim of this paper is to analyze the interaction between on-line and traditional music shops in order to understand the economic changes taking place in the music market. Music has been enjoyed since the emergence of human civilization, but until very recently only live performances could be experienced. The record industry emerged less than 100 years ago, in 1910. Today we can play CDs and MDs, as well as records and cassettes, indoors or outdoors. Recently we have seen the invention of digital music players such as Apple’s iPod and Toshiba’s Gigabit, which can play music after downloading digital music data from on-line music shops. The person can consider the various music media possibilities: CD from a traditional shop; CD from an on-line shop; Memory disc including music data from the terminals of the on-line music system in a shop; Hard disk including music data from an on-line shop. In fact, the person has to select a music medium taking into account the existence of music services from the supplier, the existence of music players and use of the Internet. In this paper the corresponding utility function is estimated using a rank-logit model.
    Date: 2006–08
  7. By: Sabrina Buyneel; Laurens Cherchye; Bram De Rock
    Abstract: We provide a .first nonparametric (revealed preference) test of the collective consumption model on the basis of experimental data. By using nonparametric testing tools and experimental data, we avoid the usual problems associated with parametric tests (e.g. non-verifiable parametric structure) and the use of ‘real life’ data sets (e.g. preference heterogeneity). In addition, our collective rationality test complements the existing nonparametric-experimental evidence on individual rationality. Focusing on dyads, we find that all observed consumption choices are consistent with the nonparametric collective rationality conditions. In fact, the consistency results for the parsimonious ‘egoistic’ collective consumption model (as a tool for describing dyads’ choice behavior) are closely similar to those for the individual rationality model (as a tool for describing individuals’.choice behavior). This suggest that for simple consumption decision settings, such as that considered in our experiment, the egoistic model may be useful for practical analysis. Still, our results also suggest that the more general collective consumption model, which accounts for consumption externalities and public consumption, can be useful even for modeling such simple decision settings. In fact, we can interpret that the appropriate model specification also depends on the specific dyad type (e.g. friends or partners; gender composition) and choice setting (e.g. public consumption or not) at hand.
    Keywords: collective consumption decisions, Generalized Axiom of Revealed Preference, nonparametric analysis, experimental data
    JEL: C14 C92 D11 D12 D13
    Date: 2006
  8. By: Lutz Schneider
    Abstract: Growth in advanced economies is essentially driven by innovation activities. From a demographic point of view the question rises, whether the trend of an ageing workforce will affect the innovation capacities of these economies. To answer this question, the paper examines on the basis of a German linked-employer-employee-dataset, whether an older workforce lowers a firm’s potential to generate product innovations. The empirical approach is based on an Ordered-logit regression model, relating a firm’s innovation potential to the age composition of its employees. The analysis provides evidence of significant age effects. The estimated age-innovation-profile follows an inverted-ushaped pattern, it peaks at the age of about 40 years. A separate estimation shows, that the technician’s and engineer’s age seems to be particularly relevant.
    Keywords: Innovation, Ageing, Linked-Employer-Employee-Analysis
    JEL: J14 O31
    Date: 2007–01
  9. By: Francisco J. Más (Universidad de Alicante); Juan Luis Nicolau (Universidad de Alicante)
    Abstract: In the advent of Customer Relationship Management, a more accurate profile of the consumer is needed. The objective of this paper is to show the usefulness of knowing consumer¿s complete utility function through his/her marginal utilities. This approach allows one to form groups of individuals with similar preferences (as traditional segmentation methods do) and to treat them individually (which represents an advance). The empirical application is carried out, on a sample of 2,127 individuals, in the context of tourism, where the customer relationship management philosophy is gaining more and more relevance. Con la llegada de la Gestión Relacional del Cliente, las organizaciones requieren un perfil del consumidor más preciso. En este contexto, el objetivo del presente trabajo consiste en proponer una segmentación apoyada en las utilidades marginales de las funciones de utilidad completas de cada individuo. Este enfoque permite formar grupos de individuos con preferencias similares (como los procedimientos habituales de segmentación) y también tratarlos de forma individual (lo que representa una novedad). La aplicación empírica se desarrolla en una muestra de 2.127 individuos en el contexto turístico, donde la filosifía de la gestión relacional del cliente está cobrando cada vez mayor importancia.
    Keywords: Gestión Relacional del Cliente, Utilidad Marginal Individual, Modelo Logit Mixto Customer Relationship Management, Marginal Individual Utility, Mixed Logit Model
    JEL: M41 G32
    Date: 2006–12
  10. By: Maria I. Marshall (Department of Agricultural Economics, College of Agriculture, Purdue University)
    Abstract: Little research has been conducted on the choice of dwelling by U.S. homeowners. Few studies have included manufactured housing into the dwelling choices available to homeowners. This study focuses on the effects of demographic and socioeconomic variables on a household’s choice to own a manufactured home. A multinomial logit model was used to determine what type of households chooses to own a manufactured home when other traditional dwelling choices are available. I found that income and education play a major role in dwelling choice.
    Keywords: Manufactured Housing; Housing Choice; Dwelling Choice, Multinomial Logit
    JEL: J11 O18 R20 R31
    Date: 2006
  11. By: Ielpo, Florian; Guégan, Dominique
    Abstract: The classical Taylor rules usually do not yield the same estimation error when working in a monthly or a quarterly framework. This brings us to the conclusion that there must be something that monthly Taylor rules can capture and that the quarterly one cannot: we postulate that it simply boils down to the fact that the target rate’s changes are irregularly spaced in time. So as to tackle this issue, we propose to split the target rate chronicle between changes in the target and the associated durations, that is the time spending between two changes in the target rate. In this framework, we propose to consider that changes in rate can be regarded as a real monetary policy decision, whereas the duration period between two changes can be related to a ”wait and see” position or some fine tuning problematic. To show that both these features of monetary policy do not react to the same fundamentals, we propose an econometric understanding of the Fed’s reaction function using a new model derived from financial econometrics that has been proposed by Engle and Russell (2005). We propose to model the changes in target rates with a classical ordered probit and the durations with an autoregressive conditional duration model. We extracted the Fed anticipations regarding inflation and activity using some factor based method, and used these factors as explanatory variables for the changes in rates and the related durations. We show that the target rate level, the scale of the change in target rate and the associated duration do not necessarily react to the same factors and if they do, the impact can be different. This empirical result supports the idea that durations and scale of the change in target rate deserve equal attention when modeling a Central Bank reaction function.
    Keywords: Taylor rule; duration models; probit models; Central Bank expectations; factor based methods.
    JEL: E52 E58
    Date: 2006–03–04
  12. By: Santugini, Marc
    Abstract: I focus on the market for movies released in the theater to measure the extent to which consumers learn about the quality of a movie from observing its market share in the release week. I derive the demand for movies using a dynamic discrete choice model in which consumers are endowed with private information about a movie and engage in as well as anticipate learning. I also assume that consumers watch a movie at most once to account for demand saturation. I depart from previous applied work on estimating the demand for movies by incorporating forward-looking behavior and observational learning. I also propose a new approach to account for demand saturation. The approach allows the decay rate for a market share to depend on consumers' past decisions, past and present movie competition, as well as past and present observational learning. The decay rate also depends on consumers' anticipation of observational learning and future schedule of movies in the theater. Given the distributional assumptions, the corresponding market shares for movies are mixing multinomial logit probabilities, taking into account consumers' forward-looking behavior and heterogeneity due, in part, to their private information. Using US market-level data, I estimate the structural parameters of demand via the maximum simulated likelihood procedure. I recover reasonable estimates for the covariates such as MPAA ratings and studio indicators. I also find evidence of observational learning. I plan to measure the effect of observational learning on demand saturation as well as the effect of anticipation of observational learning on delaying consumers from watching movies in their release weeks.
    Keywords: Motion pictures; Information; Learning; Market saturation
    JEL: L82 C13 L15 D83 D12
    Date: 2006–11–08
  13. By: García-Bermejo, Juan Carlos (Departamento de Análisis Económico (Teoría e Historia Económica). Universidad Autónoma de Madrid.)
    Abstract: “Judgement aggregation has been receiving increasing attention over recent years. Some typical impossibility results have been proved, about majority and other similar aggregation methods. Those results depend essentially on certain logical constraints borrowed from standard two- valued deductive logic. Nevertheless, the adequacy of these constraints is doubtful. In this paper, we show that by weakening the consistency conditions in a plausible way, such impossibility theorems can be reversed. We also show that the formalism habitually employed in social choice theory may convey a richer setting for analysing this sort of aggregation.”
    Keywords: Judgement aggregation; majority method; logical constraints on judgment aggregation; discursive dilemma
    JEL: D7 D70 D71

This nep-dcm issue is ©2007 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.