|
on Discrete Choice Models |
| By: | Corrado Zoppi |
| Abstract: | Research in the field of urban economics has defined methodologies to assess the degree of consensus of the local communities for policies that derive from land planning decisions. The contingent valuation methods, which are based on people’s expressed thoughts and convic-tions, allow us on the one hand to evaluate their degree of consensus, and, on the other, to in-crease the level of public information and concern towards land planning policies. Undoubt-edly, participation, concern, information and consensus must be deeply tied to each other in order to develop open processes, based on land planning policies, that generate consistency between the planning policies goals and the spatial organization of the city that the local communities would like to realize. In this essay, a case study of contingent valuation is discussed, based on the dichotomous-choice-with-follow-up technique, to rank three planning scenarios concerning the reorganiza-tion of public services and infrastructure for outdoor recreation in the coastal zone of the town of Arbus. Through this technique, the three proposals are ranked with reference to the local community preferences and attitudes concerning a set of decision criteria. The weights of the decision criteria are defined considering the results of the contingent valuation application, and utilized in a multicriteria analysis, developed through the AHP (Analytical Hierarchy Process), in order to obtain two rankings of the proposed scenarios: the first ranking is based on the results of the contingent valuation application; the second ranking comes from the weights of the decision criteria derived from the local community preferences. These two alternative rankings give the local planning context (the city administration, entre-preneurs of the profit and non-profit sectors, citizens, civic associations and committees, etc.) a comprehensive frame of the game rules of the decision-making processes, and a sound basis for discussing, recognizing and understanding their mutual convergences and conflicts. This would allow them to define an effective synthesis of their perceived needs, hopes and expecta-tions for the future spatial organization of their city, in view of the implementation of the planning policies. This essay has a marked methodological feature since a general framework- even if perfecti-ble- which should bring near technical and common knowledge is defined in the practice of city planning. This is implemented through discussion and conflict mitigation concerning the relative importance (and weights) of the decision criteria. This should lead to a more-or-less extensive convergence on policy implementation within the city planning processes. |
| Date: | 2004–08 |
| URL: | http://d.repec.org/n?u=RePEc:wiw:wiwrsa:ersa04p147&r=dcm |
| By: | António Caleiro; Conceição Rego |
| Abstract: | As it is well known, universities constitute sources of important multiplier effects on the economic activity of the regions where they are located. Plainly, in the case of economically depressed regions, the importance of universities becomes higher. This is certainly the case with the University of Évora as being located in the Alentejo, one of the poorest regions at the European Union level, it have been contributing to the attraction of economic activity. Besides the direct effect on the economic activity of the Alentejo, the University of Évora also have been exerting demographic effects, on the one hand, by allowing people to become residents on the region and, on the other hand, by attracting students which normally become residents during the period of time required to conclude their academic degrees. The paper explores this last effect by the analysis of how and why the University of Évora is chosen by students coming from all over the country (and from abroad). This analysis, which is done through the use of econometric techniques, also indicates which are the decisive factors for the attraction exerted by the University of Évora, in general, and by its degree courses, in particular, on the candidate students. KEYWORDS: Decision Analysis, Discrete Choice Models, Portugal, Universities JEL CLASSIFICATION: C21, R12, R23 |
| Date: | 2004–08 |
| URL: | http://d.repec.org/n?u=RePEc:wiw:wiwrsa:ersa04p23&r=dcm |
| By: | Guillaume Pouyanne |
| Abstract: | The influence of urban form on travel patterns is of growing interest among researchers. It has been notably argued that high density, mixed land use settlements reduce automobile use and distances travelled, hence energy consumption per capita. A precise characterization of urban form calls analysis at an infra-urban level. We have questioned the interaction between land use and mobility in the metropolitan area of Bordeaux, France, by using OLS regressions for usual transportation variables and a multinomial logit model for modal shares. The results confirm a strong influence of both residential and firm density on mobility patterns. Mixed land use patterns doesn’t seem to influence mobility. Some economic and demographic characteristics have an influence on travel patterns. Thus it is unavoidable to take them in account. But sometimes it leads to a logical indecision, and it is difficult to determine the direction of the causal relationship. Keywords : urban sprawl, density, compact city, land use – mobility interaction JEL classification : R12, R14, R41 |
| Date: | 2004–08 |
| URL: | http://d.repec.org/n?u=RePEc:wiw:wiwrsa:ersa04p244&r=dcm |
| By: | Michiel de Bok |
| Abstract: | This paper describes the research approach and first empirical results of the estimation of discrete choice models that describe the location decision of moving firms. The model is based on random utility theory and features systematic choice sets to account for the choice context at the highest level of spatial detail (address-level). Firms are analysed categorised to their mobility profile. These mobility profiles are homogenous groups of firms with similar mobility characteristics that are a priori assumed. The models are tested on an extensive revealed preference dataset with firm migration observations in South Holland. To avoid correlations between variables a variety of composed accessibility variables have been constructed that describe the distances to the physical infrastructure or that are an aggregated form of potential accessibility. The location attributes of alternatives have been completed with the business environment type and the rental level. The results are first of all valuable for the development of a simulation model for firm location but the empirical results also yields insight into the spatial behaviour and location preference of firms. Although further research is necessary, the presented addresses some challenges in modelling the spatial behaviours of firms in an urban environment. Therefore the presented approach holds seems valuable for the development of a simulation model for location decisions of moving firms and offers good possibilities for future research. |
| Date: | 2004–08 |
| URL: | http://d.repec.org/n?u=RePEc:wiw:wiwrsa:ersa04p338&r=dcm |
| By: | Roberto Basile; Davide Castellani; Antonello Zanfei |
| Abstract: | We examine the determinants of multinational firms’ location choices in Europe by estimating a nested logit model on a data-set of 5,761 foreign subsidiaries established in 55 regions in 8 EU countries over the period 1991-1999. We find that firms perceive regions across different countries as more similar than regions within national borders. This might be revealing that the process of European integration has reduced the national specificities perceived by multinationals and that regions within Europe compete to attract FDIs more across than within countries. Controlling for regional market size and potential, agglomeration economies and labor markets conditions, we also find that EU regional policy, captured by Cohesion Funds and Objective 1 eligibility, played a significant role in attracting multinationals, thus mitigating the agglomeration forces at work. Differences emerge in determinants of EU and US multinationals location choices, with special reference to the role of labor markets. |
| Date: | 2004–08 |
| URL: | http://d.repec.org/n?u=RePEc:wiw:wiwrsa:ersa04p37&r=dcm |
| By: | Masaya Kawano; Tetsunobu Yoshitake; Hiroshi Tatsumi; Yoshitaka Kajita |
| Abstract: | The complex problems shared by many cities throughout Japan are evidence of the impacts of land use plans that have been poorly designed and managed. Most of the existing plans in Japan have focused on the metropolitan areas but nowadays the physical layout or land use of communities is fundamental to sustainability. Community sustainability requires a transition from poorly-managed large-scale plans to land use planning practices at the community scale that maintain efficient infrastructures, and ensure close-knit neighborhoods and a sense of community. This paper provides a scheme for discussing the residential choice of people at the community scale in a local city in Japan in order to help local communities or local authorities concerned with suitable land use planning. First, this paper gives the key principles of residential choice behavior through the statistical analysis of the revealed preference of people who actually made the decision to choose the location of their new residence. Some interesting results are a bigger correlation than expected between the location of residence and the place of work, and a strong attachment of movers to their old communities. The latter half of this paper describes a modeling process for specifying the residential choice at the community scale. The discrete choice model adopted in the present study is a conventional disaggregate logit model that is capable of representing complicated individual choice behavior while they are changing their place of residence. |
| Date: | 2004–08 |
| URL: | http://d.repec.org/n?u=RePEc:wiw:wiwrsa:ersa04p40&r=dcm |
| By: | Yin-Yen Tseng |
| Abstract: | The reliability and scheduling delay of travel time attributes have been considered as important factors in traveler’s decision making. Numerous studies have attempted to incorporate travel time reliability and scheduling delay early/late attributes into traveler’s choice models since the last decade. However, there is still a wide-ranging debate on empirical valuations, and substantial differences of estimation values are shown among studies. Our aim in this study is to investigate several unresolved issues in the empirical valuation of reliability and scheduling delay delay/late and estimate these effects by means of a multivariate statistical technique: meat-analysis. The main finding is that including all reliability and scheduling delay early/late attributes in choice model would lead to lower estimated values for these attributes. We also find that the stated preference data produce substantial lower values for the ratio between scheduling delay early/late and travel time coefficients and the possible explanation may be the misperception error together with the risk aversion attitude of travelers. Key words: travel time reliability, scheduling delay early, scheduling delay late, meta-analysis. |
| Date: | 2004–08 |
| URL: | http://d.repec.org/n?u=RePEc:wiw:wiwrsa:ersa04p415&r=dcm |
| By: | Patrizia Riganti; Annamaria Nese; Ugo Colombino |
| Abstract: | This paper discusses ways of improving the management of cultural heritage sites and cities, focusing on new forms of involvement and public participation based on public preferences’ elicitation. The problem of city governance and of the appropriate level of democratic participation needs an integrated approach, capable of bridging the practice of urban design, conservation of the built environment and decision-making support system. This paper reports results from a survey using conjoint choice approach questions to elicit people’s preferences for cultural heritage management strategies for an outstanding world heritage site: the Temples of Paestum, in Italy. The potential of the above-mentioned methodologies’ within the current cultural heritage research scenario is also discussed. |
| Date: | 2004–08 |
| URL: | http://d.repec.org/n?u=RePEc:wiw:wiwrsa:ersa04p437&r=dcm |
| By: | Daniel Shefer; Mordechai Cohen; Shlomo Bekhor |
| Abstract: | This paper is concerned with the development of varieties and fertilization techniques of greenhouse tomatoes, and their spatial diffusion in the northwestern region of the Negev in Israel. The main objective of the paper is to identify the factors affecting the farmers’ decision to adopt innovations and the factors inducing the process of knowledge-diffusion in the rural region. The approach adopted is the use of discrete choice models based on random utility theory. Results of the empirical analysis when applying the disaggregate Logit Model indicate that the regional, local and individual attributes have a significant bearing on the farmers’ decision-making process in regard to choosing among alternative tomato varieties and fertilization techniques. The findings indicate that the models constructed for this study may be used as a planning tool for the purpose of evaluating the effect of different factors on the spatial diffusion of innovations in rural regions. The results of the research could also assist decision-makers in formulating development policies for rural regions. Keywords: Spatial diffusion; discrete choice models; greenhouse tomatoes; nested logit |
| Date: | 2004–08 |
| URL: | http://d.repec.org/n?u=RePEc:wiw:wiwrsa:ersa04p484&r=dcm |
| By: | Stephane Hess; John W. Polak |
| Abstract: | Parking policy is an important component of contemporary travel demand management policies. The effectiveness of many parking policy measures depends on influencing parking type choice, so that understanding the factors affecting these choices is of considerable practical importance. Yet, academic interest in this issue has been, at best, intermittent. This paper reports the results of an analysis of parking choice behaviour, based on a stated preference (SP) dataset, collected in various city centre locations in the UK. The analysis advances the state of the art in the analysis of parking choice behaviour by using a mixed multinomial logit (MMNL) model, capable of accommodating random heterogeneity in travellers’ tastes and potential correlation structure induced by repeated observations being made of the same individuals. The results of the analysis indicate that taste heterogeneity is a major factor in parking type choice. Accommodating this heterogeneity leads to significantly different conclusions regarding the influence of substantive factors such as access, search and egress time and on the treatment of potential fines for illegal parking. It also has important effects on the implied willingness to pay for timesavings and on the distribution of this willingness in the population. Our analysis also reveals important differences in parking behaviour across different journey purposes, and the models reveal an important locational effect, in such that the results of the analysis vary substantively across the three locations used in the SP surveys. Finally, the paper also discusses a number of technical issues related to the specification of taste heterogeneity that are of wider significance in the application of the MMNL model. |
| Date: | 2004–08 |
| URL: | http://d.repec.org/n?u=RePEc:wiw:wiwrsa:ersa04p60&r=dcm |
| By: | Stephane Hess |
| Abstract: | In this paper, we describe part of an ongoing study of airport choice for passengers departing from the San Francisco Bay area. The aim of the present paper is to test for the prevalence of taste heterogeneity across travellers, using the Mixed Multinomial Logit (MMNL) model. Our results indicate the presence of significant levels of heterogeneity in tastes, especially with respect to the sensitivity to access time, characterised by significant (deterministic) variation between groups of travellers (business/leisure, residents/visitors) as well as random variation within groups of travellers. Our analysis reinforces earlier findings showing that business travellers are far less sensitive to fare increases than leisure travellers, and are willing to pay a higher price for decreases in access time (and generally also increases in frequency) than is the case for leisure travellers. Finally, the results show that the random variation between business travellers in terms of sensitivity to access time is more pronounced than that between leisure travellers, as is the case for visitors when compared to residents. |
| Date: | 2004–08 |
| URL: | http://d.repec.org/n?u=RePEc:wiw:wiwrsa:ersa04p61&r=dcm |
| By: | Isabelle Thomas; Ann Verhetsel; Frank Witlox; Hakim Hammadou; Hans Tindemans; Dries Van Hofstraeten |
| Abstract: | This paper considers different alternatives for including spatial aspects within the activity-based approach for modeling destination choices. The study area is the urban agglomeration of Antwerpen (Belgium); the city and its suburbs are considered. Individual travel surveys are used. The paper pays particular attention to the inclusion of space within the decision context by including specific land-use explanatory variables generated by Geographical Information Systems. A preliminary geographical analysis is performed in order to represent the city by a limited set of destinations (n = 33) and to characterize those zones in terms of land use. Discrete choice modelling is used: each individual faces the total set of spatial destination alternatives. Several modelling approaches are explored and compared in terms of utility function (for instance Box-Cox; random coefficients) and in terms of global formulation (multinomial logit versus nested logit). The mixed nested logit formulation is selected as best and the parameter estimations are interpreted; it shows the importance of space within destination choices. This paper provides a useful background for decision-makers and planners of transportation policy related to individual mobility patterns. Keywords Discrete choice model, activity-based approach, GIS, land use, urban mobility, Antwerpen |
| Date: | 2004–08 |
| URL: | http://d.repec.org/n?u=RePEc:wiw:wiwrsa:ersa04p70&r=dcm |
| By: | Paulo Guimaraes (Medical University of South Carolina); Richard Lindrooth (Medical University of South Carolina) |
| Abstract: | In this paper we provide a Random-Utility based derivation of the Dirichlet-Multinomial regression and posit it as a convenient alternative for dealing with overdispersed multinomial data. We show that this model is a natural extension of McFadden's conditional logit for grouped data and show how it relates with count models. Finally, we use a data set on patient choice of hospitals to illustrate an application of the Dirichlet-Multinomial regression. |
| Keywords: | dirichlet-multinomial, grouped conditional logit, hospital choice, overdispersion |
| JEL: | C25 C21 I11 |
| Date: | 2005–09–01 |
| URL: | http://d.repec.org/n?u=RePEc:wpa:wuwpem:0509001&r=dcm |