|
on Discrete Choice Models |
| By: | Anna Gottard (Dipartimento di Statistica, Informatica, Applicazioni "G. Parenti", Università di Firenze); Giorgio Calzolari (Dipartimento di Statistica, Informatica, Applicazioni "G. Parenti", Università di Firenze) |
| Abstract: | Multiple-membership logit models with random effects are logit models for clustered binary data, where each statistical unit can belong to more than one group. For these models, the likelihood function is analytically intractable. We propose two different approaches for parameter estimation: data cloning and indirect inference. Data cloning computes maximum likelihood estimates, through the posterior distribution of an adequate Bayesian model fitted on cloned data. We implement a data cloning algorithm specific for the case of multiple-membership models. Indirect inference is a non-likelihood based method which uses an auxiliary model to select sensible estimates. We propose an auxiliary model having the same dimension of parameter space as the target model, which is particularly convenient to reach good estimates very fast. A Monte Carlo experiment compares the two approaches on a set of simulated data. We report also Bayesian posterior mean and INLA hybrid data cloning estimates for comparison. Simulations show a negligible loss of efficiency for the indirect inference estimator, compensated by a relevant computational gain. The approaches are then illustrated with a real example on matched paired data. |
| Keywords: | Binary data, Bradley Terry models, intractable likelihood, integrated nested Laplace approximation, non-hierarchical random effects models |
| JEL: | C51 |
| Date: | 2014–07 |
| URL: | http://d.repec.org/n?u=RePEc:fir:econom:wp2014_07&r=dcm |
| By: | Loeffler, Max (ZEW Mannheim); Peichl, Andreas (ZEW Mannheim); Siegloch, Sebastian (University of Mannheim) |
| Abstract: | There is still considerable dispute about the magnitude of labor supply elasticities. While differences in micro and macro estimates are recently attributed to frictions and adjustment costs, we show that relatively low labor supply elasticities derived from microeconometric models can also be explained by modeling assumptions with respect to wages. Specifically, we estimate 3,456 structural labor supply models each representing a plausible combination of frequently made choices. While most model assumptions do not systematically affect labor supply elasticities, our analysis shows that the results are very sensitive to the treatment of wages. In particular, the often-made but highly restrictive independence assumption between preferences and wages is key. To overcome this restriction, we propose a flexible estimation strategy that nests commonly used models. We show that loosening the exogeneity assumption leads to labor supply elasticities that are much higher. |
| Keywords: | labor supply, elasticity, random utility models, wages |
| JEL: | C25 C52 H31 J22 |
| Date: | 2014–06 |
| URL: | http://d.repec.org/n?u=RePEc:iza:izadps:dp8281&r=dcm |
| By: | Wenyun Tang; David Levinson (Nexus (Networks, Economics, and Urban Systems) Research Group, Department of Civil Engineering, University of Minnesota) |
| Abstract: | Few empirical studies of revealed route characteristics have been reported in the literature. This study challenges the widely applied shortest path assumption by evaluating routes followed by residents of the Minneapolis - St. Paul metropolitan area, as measured by the GPS Component of the 2011 Twin Cities Travel Behavior Inventory. It finds that most travelers used paths longer than the shortest path. Some reasons for this are conjectured. |
| Keywords: | Rationality, Route Choice, User Equilibrium, GPS Study, Travel Behavior, Networks |
| JEL: | R40 |
| Date: | 2014 |
| URL: | http://d.repec.org/n?u=RePEc:nex:wpaper:peoplearenotrational&r=dcm |
| By: | Jesus Gonzalez-Feliu (LET - Laboratoire d'économie des transports - CNRS : UMR5593 - École Nationale des Travaux Publics de l'État [ENTPE] - Université Lumière - Lyon II); Joelle Morana (LET - Laboratoire d'économie des transports - CNRS : UMR5593 - École Nationale des Travaux Publics de l'État [ENTPE] - Université Lumière - Lyon II) |
| Abstract: | This paper aims to propose, via an experimental collaborative decision support method, to define a grid of indicators and a reference situation database to measure the sustainable performance of urban logistics pooling systems. To do this, we start by defining the notion of sustainability in the 4As approach, after what we identify the main sustainability indicators from an overview of the literature, and class them into four categories (one for each A of the approach). Then, a group of 20 experts is required and an iterative experimental collaborative decision making method is applied to the group to converge to the concordance of a set of indicators. The method allowed us to define a hierarchic dashboard agreed by all experts with 7 main indicators and 9 secondary indicators. Moreover, the experts signaled the need of defining a unified basis of comparison to estimate initial situations. To do this, we proposed a database of urban routes from the French Surveys on Urban Goods Transport. This method has the advantage of proposing a dashboard agreed by all involved stakeholders. The proposed dashboard is an example and to provide a more unified one the experience has to be iterated using different groups of decision makers. Therefore, this paper shows the patterns to reproduce it, since the method is able to be replicated in any context of group decision in urban logistics. The originality of the paper arises on the use of an experimental group decision method using a group with a majority of practitioners, and to validate it by consensus. |
| Keywords: | logistics pooling; sustainable development; group decision support; distribution; consensus |
| Date: | 2014 |
| URL: | http://d.repec.org/n?u=RePEc:hal:wpaper:halshs-01053887&r=dcm |