|
on Discrete Choice Models |
| By: | André de Palma (University of Cergy-Pontoise, THEMA, France and Ecole Nationale des Ponts et Chaussée, France. Member of the Institut universitaire de France); Nathalie Picard (University of Cergy-Pontoise, THEMA, France and INED); Paul Waddell (University of Washington at Seattle, Department of Urban Design and Planning) |
| Abstract: | Discrete choice models are based on the idea that each user can choose both freely and independently from other users in a given set of alternatives. But this is not the case in several situations. In particular, limitations and interactions can occur when the number of available products of one type is smaller than the total demand for this type. As a consequence, some individuals can be denied their preferred choice. We develop a methodology to address those constraints and we apply it to residential location choice, where our empirical data suggest that availability constraints may bias actual choices. The analysis provides some theoretical developments and elaborates an iterative procedure for estimating demand in the presence of capacity constraints. The empirical application relies on the location choice model developed and estimated in [6] for Ile de France (Paris region) and generalizes it to integrate capacity constraints. |
| Keywords: | Residential location, constrained Logit, capacity constraints, sampling, Ilede- France |
| JEL: | C35 R21 R31 |
| Date: | 2007 |
| URL: | http://d.repec.org/n?u=RePEc:ema:worpap:2007-04&r=dcm |
| By: | Cizek,Pavel (Tilburg University, Center for Economic Research) |
| Abstract: | The binary-choice regression models such as probit and logit are used to describe the effect of explanatory variables on a binary response variable. Typically estimated by the maximum likelihood method, estimates are very sensitive to deviations from a model, such as heteroscedasticity and data contamination. At the same time, the traditional robust (high-breakdown point) methods such as the maximum trimmed likelihood are not applicable since, by trimming observations, they induce the separation of data and non-identiffication of parameter estimates. To provide a robust estimation method for binary-choice regression, we consider a maximum symmetrically-trimmed likelihood estimator (MSTLE) and design a parameter-free adaptive procedure for choosing the amount of trimming. The proposed adaptive MSTLE preserves the robust properties of the original MSTLE, signifficantly improves the finite-sample behavior of MSTLE, and additionallyfensures asymptotic efficiency of the estimator under no contamination. The results concerning the trimming identiffication, robust properties, and asymptotic distribution of the proposed method are accompanied by simulation experiments and an application documenting the finite-sample behavior of some existing and the proposed methods. |
| Keywords: | asymptotic efficiency;binary-choice regression;breakdown point;maximum likelihood estimation;robust estimation;trimming |
| JEL: | C13 C20 C21 C22 |
| Date: | 2007 |
| URL: | http://d.repec.org/n?u=RePEc:dgr:kubcen:200712&r=dcm |
| By: | Benoit Dostie (IEA, HEC Montréal); David Sahn |
| Abstract: | In this paper, we estimate a model of labor market dynamics among individuals in Romania using panel data for three years, 1994 to 1996.Our motivation is to gain insight into the functioning of the labor market and how workers are coping during this period of economic liberalization and transformation that began in 1990. Our models of labor market transitions for men and women examine changing movements in and out of employment, unemployment, and self-employment, and incorporate specific features of the Romanian labor market, such as the social safety net. We take into account demographic characteristics, state dependence, and individual unobserved heterogeneity by modeling the employment transitions with a dynamic mixed multinomial logit. |
| Date: | 2006–12 |
| URL: | http://d.repec.org/n?u=RePEc:iea:carech:0617&r=dcm |
| By: | Guido Citoni (University "La Sapienza" Rome and DULBEA, Free University of Brussels.) |
| Abstract: | Using the data collected for the year 2004 in the Belgian Health Survey, we aim to show that, controlling for all the determinants of self-reported health state, there is a residual effect of geographic location on the self-assessed health, namely a more favourable scoring for individuals that are resident both in the region of Brussels and in the region of Walloonia, with respect to individuals that are resident in the Flanders. Regional effects do not change either if we take account of supply of health services or if we control for their utilization. Moreover the effect of past level of health is encompassed to test for habituation, and the results still hold. The above findings can be used both to construct “equivalent expected QALY’s or EEQ” , i.e. the average quality adjusted life years that a newborn, taking account of the different average level of health at the regional level, can expect to experience in the different geographical areas of Belgium (the three regions have approximately the same EEQ), and to predict a “need factor” to be used either for equity analysis or to ascertain its evolution in time. |
| Keywords: | Self-assessed health; Quality of life; QALY’s; Regions of Belgium; Health Survey; Ordered Probit. |
| JEL: | I10 I12 I19 |
| Date: | 2007–01 |
| URL: | http://d.repec.org/n?u=RePEc:dul:wpaper:07-01rs&r=dcm |
| By: | Jacob L. Vigdor |
| Abstract: | Many observers argue that urban revitalization harms the poor, primarily by raising rents. Others argue that urban decline harms the poor by reducing job opportunities, the quality of local public services, and other neighborhood amenities. While both decay and revitalization can have negative effects if moving costs are sufficiently high, in general the impact of neighborhood change on utility depends on the strength of price responses to neighborhood quality changes. Data from the American Housing Survey are used to estimate a discrete choice model identifying households' willingness-to-pay for neighborhood quality. These willingness-to-pay estimates are then compared to the actual price changes that accompany observed changes in neighborhood quality. The results suggest that price increases associated with revitalization are smaller than most households' willingness to pay for neighborhood improvements. The results imply that, in general, neighborhood revitalization is more favorable than neighborhood decline. |
| JEL: | D1 R21 R31 |
| Date: | 2007–03 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:12955&r=dcm |
| By: | Mirta B. Gordon (TIMC - IMAG - Techniques de l'Imagerie, de la Modélisation et de la Cognition - [CNRS : UMR5525] - [Université Joseph-Fourier - Grenoble I][Institut National Polytechnique de Grenoble - INPG]); Jean-Pierre Nadal (CAMS - Centre d'analyse et de mathématique sociale - [CNRS : UMR8557] - [Ecole des Hautes Etudes en Sciences Sociales], LPS - Laboratoire de Physique Statistique de l'ENS - [CNRS : UMR8550] - [Université Pierre et Marie Curie - Paris VI][Université Denis Diderot - Paris VII] - [Ecole Normale Supérieure de Paris]); Denis Phan (CREM - Centre de Recherche en Economie et Management - [CNRS : UMR6211] - [Université Rennes I][Université de Caen], GEMAS - Groupe d'étude des méthodes de l'analyse sociologique - [CNRS : UMR8598] - [Université Paris-Sorbonne - Paris IV]); Viktoriya Semeshenko (TIMC - IMAG - Techniques de l'Imagerie, de la Modélisation et de la Cognition - [CNRS : UMR5525] - [Université Joseph-Fourier - Grenoble I][Institut National Polytechnique de Grenoble - INPG]) |
| Abstract: | We consider a model of socially interacting individuals that make a binary choice in a context of positive additive endogenous externalities. It encompasses as particular cases several models from the sociology and economics literature. We extend previous results to the case of a general distribution of idiosyncratic preferences, called here Idiosyncratic Willingnesses to Pay (IWP).<br /><br />Positive additive externalities yield a family of inverse demand curves that include the classical downward sloping ones but also new ones with non constant convexity. When $j$, the ratio of the social influene strength to the standard deviation of the IWP distribution, is small enough, the inverse demand is a classical monotonic (decreasing) function of the adoption rate. Even if the IWP distribution is mono-modal, there is a critical value of $j$ above which the inverse demand is non monotonic, decreasing for small and high adoption rates, but increasing within some intermediate range. Depending on the price there are thus either one or two equilibria.<br /><br />Beyond this first result, we exhibit the {\em generic} properties of the boundaries limiting the regions where the system presents different types of equilibria (unique or multiple). These properties are shown to depend {\em only} on qualitative features of the IWP distribution: modality (number of maxima), smoothness and type of support (compact or infinite).<br />The main results are summarized as {\em phase diagrams} in the space of the model parameters, on which the regions of multiple equilibria are precisely delimited. |
| Keywords: | discrete choice; social influence; externalities; heterogeneous agents; socioeconomic behavior |
| Date: | 2007–03–07 |
| URL: | http://d.repec.org/n?u=RePEc:hal:papers:halshs-00135405_v1&r=dcm |
| By: | Eric A. Hanushek; Kuzey Yilmaz |
| Abstract: | An important element in considering school finance policies is that households are not passive. Instead they respond to policies with a combination of modified residential choice and political choice of tax levels. The highly stylized decision models of most existing analyses, however, lead to conerns about the policy evaluations. In our general equilibrium model of residential location and community choice, households base optimizing decisions on commuting costs, school quality, and land rents. With both centralized and decentralized employment, the resulting equilibrium has heterogeneous communities in terms of income and tastes for schools. This model is used to analyze a series of conventional policy experiments, including school district consolidation, district power utilization, and different equalization devices. The important conclusion is that welfare falls for all families with the restrictions in choice that are implied by these approaches. |
| JEL: | H4 I2 R1 R51 |
| Date: | 2007–03 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:12960&r=dcm |
| By: | Paul Dolan; Oyeyemi Oluboyede; Jennifer Roberts (Department of Economics, The University of Sheffield) |
| Abstract: | Expected Utility (EU) theory is the standard economic model of individual preferences under uncertainty. However, observed violations of the axioms of EU have generated interest in the incorporation of a stochastic element into deterministic models of decision-making. Previous empirical investigation of the theories of stochastic choice has involved monetary gambles in risky conditions using convenience samples of students. The aim of this study is to test generalisations of these models in the context of eliciting the preferences of the general public over health states under conditions of certainty. Our findings lend support to the `white noise´ stochastic specification of Hey and Orme (1994) which indicates that the stronger the preferences of an individual, the less likely they are to make a mistake and attach a lower value to their truly preferred alternative. JEL Classification: D0 Key words: Stochastic preferences, utility assessment, expected utility theory. |
| Keywords: | Stochastic preferences, utility assessment, expected theory |
| JEL: | D0 |
| Date: | 2005–11 |
| URL: | http://d.repec.org/n?u=RePEc:shf:wpaper:2005017&r=dcm |
| By: | Bernd Hayo (Faculty of Business Administration and Economics, Philipps Universitaet Marburg); Hiroyuki Ono (Faculty of Economics, Toyo Universtiy) |
| Abstract: | This paper studies attitudes about who should provide for the livelihood of the elderly in two aging societies, namely Germany and Japan. Applying an ordered logit model to individual data from representative public opinion surveys, it is analysed which socio-demographic, economic or political variables help to explain people’s attitudes on whether the government or individuals should be responsible for the livelihood of the elderly. We find that while higher income makes people more inclined towards the individual option, age is found to do the opposite in both countries. We conjecture that this age effect is related to the level of knowledge about the current situation of the public pension system. We also find that the part-time work status significantly affects attitudes in both countries, but not the same way. It affects adversely the inclination towards a government-based pension system in the case of Japan but positively in Germany. Other significant influences are the pensioner status of the respondents in Japan and their political position in the case of German data. |
| Keywords: | Livelihood of elderly, pension reform, public attitudes, aging societies, Germany, Japan |
| JEL: | H55 Z10 |
| Date: | 2007 |
| URL: | http://d.repec.org/n?u=RePEc:mar:volksw:200703&r=dcm |
| By: | A. PRINZIE; D. VAN DEN POEL |
| Abstract: | The acquisition process of consumer durables is a ‘sequence’ of purchase events. Priority-pattern research exploits this ‘sequential order’ to describe a prototypical acquisition order for durables. This paper adds a predictive perspective to increase managerial relevance. Besides order information, the acquisition sequence also reveals precise timing between purchase events (‘sequential duration’) as examined in the literature on durable replacement and time-to-first acquisition. This paper bridges the gap between priority-pattern research and research on duration between durable acquisitions to improve the prediction of the product group the customer might acquire his next durable from, i.e. Next-Product-to-Buy (NPTB) model. We evaluate four multinomial-choice models incorporating: 1) general covariates, 2) general covariates and sequential order, 3) general covariates and sequential duration, and 4) general covariates, sequential order and duration. The results favor the model including general covariates and duration information (3). The high predictive value of sequentialduration information emphasizes the predictive power of duration as compared to order information. |
| Keywords: | cross-sell, sequence analysis, choice modeling, durable goods, analytical CRM |
| Date: | 2007–01 |
| URL: | http://d.repec.org/n?u=RePEc:rug:rugwps:07/442&r=dcm |
| By: | Monica Hernandez; Stephen Pudney; Ruth Hancock (Department of Economics, The University of Sheffield) |
| Abstract: | We estimate parametric and semi-parametric binary choice models of benefit take-up by British pensioners and use a revealed preference argument to infer the cash-equivalent value of disutility arising from stigma or complexity of the claims process. These implicit costs turn out to be relatively small, averaging about £3-4 per week across Income Support recipients. Using the Foster-Greer-Thorbecke measure of poverty among pensioners, we find that allowing for implicit claim costs incurred by benefit recipients raises the measured degree of poverty by not more than 13%. |
| Keywords: | Benefit take-up, Program participation, pensions, welfare, poverty |
| JEL: | C25 D63 H55 I32 I38 |
| Date: | 2006–04 |
| URL: | http://d.repec.org/n?u=RePEc:shf:wpaper:2006004&r=dcm |