|
on Discrete Choice Models |
| By: | Giulio Bottazzi; Ugo Gragnolati; Fabio Vanni |
| Abstract: | A stochastic discrete choice model and its related estimation method are presented which allow to disentangle non-linear externalities from the intrinsic features of the objects of choice and from the idiosyncratic preferences of agents. Having veried for the ergodicity of the underlying stochastic process, parameter estimates are obtained through numerical methods and so is their statistical signicance. In particular, optimization rests on successive parabolic interpolation. Finally, the model and its related estimation method are applied to the case of rm localization using Italian sectoral census data. |
| Keywords: | Externalities, Heterogeneity, Computational methods, Firm localization |
| Date: | 2014–01–15 |
| URL: | http://d.repec.org/n?u=RePEc:ssa:lemwps:2014/01&r=dcm |
| By: | Sumit Kunnumkal; Kalyan Talluri |
| Abstract: | The choice network revenue management (RM) model incorporates customer purchase behavior as customers purchasing products with certain probabilities that are a function of the offered assortment of products, and is the appropriate model for airline and hotel network revenue management, dynamic sales of bundles, and dynamic assortment optimization. The underlying stochastic dynamic program is intractable and even its certainty-equivalence approximation, in the form of a linear program called Choice Deterministic Linear Program (CDLP) is difficult to solve in most cases. The separation problem for CDLP is NP-complete for MNL with just two segments when their consideration sets overlap; the affine approximation of the dynamic program is NP-complete for even a single-segment MNL. This is in contrast to the independentclass (perfect-segmentation) case where even the piecewise-linear approximation has been shown to be tractable. In this paper we investigate the piecewise-linear approximation for network RM under a general discrete-choice model of demand. We show that the gap between the CDLP and the piecewise-linear bounds is within a factor of at most 2. We then show that the piecewiselinear approximation is polynomially-time solvable for a fixed consideration set size, bringing it into the realm of tractability for small consideration sets; small consideration sets are a reasonable modeling tradeoff in many practical applications. Our solution relies on showing that for any discrete-choice model the separation problem for the linear program of the piecewise-linear approximation can be solved exactly by a Lagrangian relaxation. We give modeling extensions and show by numerical experiments the improvements from using piecewise-linear approximation functions. |
| Keywords: | Optimization Techniques; Programming Models; Dynamic Analysis; Air Transportation ; Sports; Gambling; Recreation; Tourism; Production Management |
| JEL: | C61 L93 L83 M11 |
| Date: | 2014–01 |
| URL: | http://d.repec.org/n?u=RePEc:upf:upfgen:1409&r=dcm |
| By: | Hubert JAYET (Université Lille 1, EQUIPPE); Glenn RAYP (Ghent University, SHERPPA); Ilse RUYSSEN (UNIVERSITE CATHOLIQUE DE LOUVAIN, Institut de Recherches Economiques et Sociales (IRES) and Ghent University, SHERPPA); Nadiya UKRAYINCHUK (Université de Lille 2, EQUIPPE) |
| Abstract: | This paper analyses migratory streams to Belgian municipalities between 1994-2007. The Belgian population register constitutes a rich and unique database of yearly migrant in inflows and stocks broken down by nationality, which allows us to empirically explain the location choice of immigrants at municipality level. Specifically, we aim at separating the network effect, captured by the number of previous arrivals, from other location-specific characteristics such as local labor or housing market conditions and the presence of public amenities. We expect labor and housing market variables to operate at different levels and develop a nested model of location choice in which an immigrant first chooses a broad area, roughly corresponding to a labor market, and subsequently chooses a municipality within this area. We find that the spatial repartition of immigrants in Belgium is determined by both network effects and local characteristics. The determinants of local attractiveness vary by nationality, as expected, but for all nationalities, they seem to dominate the impact of network effects. |
| Keywords: | International migration, Location choice, Network effects, Nested logit |
| Date: | 2014–01–20 |
| URL: | http://d.repec.org/n?u=RePEc:ctl:louvir:2014004&r=dcm |