|
on Discrete Choice Models |
| By: | José Apesteguía; Miguel Angel Ballester |
| Abstract: | Discrete choice methods are often used for the estimation of time preferences. We show that these methods have pervasive problems when based on random utility models, for which cases our results establish that the probability of selecting a later option over an earlier one may be greater for higher levels of impatience. This could have profound implications, not only in the experimental estimation of time preferences, but also in a wide variety of empirical papers using such models in dynamic settings. Alternatively, we also show that discrete choice methods built on random preference models are always free of all such problems. |
| Keywords: | discrete choice, structural estimation, time, discounting, random utility models, random preference models |
| JEL: | C25 D90 |
| Date: | 2014–09 |
| URL: | http://d.repec.org/n?u=RePEc:bge:wpaper:787&r=dcm |
| By: | Darryl Holden (Department of Economics, University of Strathclyde); Roger Perman (Department of Economics, University of Strathclyde) |
| Abstract: | The paper considers the use of artiï¬cial regression in calculating different types of score test when the logâˆ'likelihood is based on probabilities rather than densities. The calculation of the information matrix test is also considered. Results are specialised to deal with binary choice (logit and probit) models. |
| Keywords: | score test, information matrix, artificial regression |
| JEL: | C1 C2 C4 C12 |
| Date: | 2014–10 |
| URL: | http://d.repec.org/n?u=RePEc:str:wpaper:1410&r=dcm |
| By: | Aiste Ruseckaite (Erasmus University Rotterdam); Peter Goos (Universiteit Antwerpen, Belgium); Dennis Fok (Erasmus University Rotterdam) |
| Abstract: | Consumer products and services can often be described as mixtures of ingredients. Examples are the mixture of ingredients in a cocktail and the mixture of different components of waiting time (e.g., in-vehicle and out-of-vehicle travel time) in a transportation setting. Choice experiments may help to determine how the respondents' choice of a product or service is affected by the combination of ingredients. In such studies, individuals are confronted with sets of hypothetical products or services and they are asked to choose the most preferred product or service from each set. However, there are no studies on the optimal design of choice experiments involving mixtures. We propose a method for generating an optimal design for such choice experiments. To this end, we first introduce mixture models in the choice context and next present an algorithm to construct optimal experimental designs, assuming the multinomial logit model is used to analyze the choice data. To overcome the problem that the optimal designs depend on the unknown parameter values, we adopt a Bayesian D-optimal design approach. We also consider locally D-optimal designs and compare the performance of the resulting designs to those produced by a utility-neutral (UN) approach in which designs are based on the assumption that individuals are indifferent between all choice alternatives. We demonstrate that our designs are quite different and in general perform better than the UN designs. |
| Keywords: | Bayesian design, Choice experiments, D-optimality, Experimental design, Mixture coordinate-exchange algorithm, Mixture experiment, Multinomial logit model, Optimal design |
| JEL: | C01 C10 C25 C61 C83 C90 C99 |
| Date: | 2014–05–09 |
| URL: | http://d.repec.org/n?u=RePEc:dgr:uvatin:20140057&r=dcm |
| By: | Sylvia Bleker (VU University Amsterdam, the Netherlands); Christiaan Behrens (VU University Amsterdam, the Netherlands); Paul Koster (VU University Amsterdam, the Netherlands); Erik T. Verhoef (VU University Amsterdam, the Netherlands) |
| Abstract: | This article investigates competition in a market with an emerging technology using a discrete choice model to analyze demand and welfare. We focus on industry structure and investigate the impact of different market structures on demand for the new technology and on welfare. The car market serves as a prime example of such a market, where electric vehicles (EV’s) represent the new technology competing with standard cars with internal combustion engines (ICV’s). To analyze such a market, we use a nested logit model. In contrast to earlier literature, we allow firms to be asymmetric and active in multiple nests, with different numbers of variants in each nest, which can add up to any market share. Additionally, we add to existing literature by considering the case where substitutability between firms is stronger than between technologies, by nesting products by technology instead of by firm. We find implicit analytical solutions for the equilibrium mark-ups which can be used when there are two nests in the market; within that restriction firms can be asymmetric. Numerically, we find that EV sales are higher if offered by a new entrant only selling EV’s as opposed to when it is supplied by a firm selling variants of both types. We present an index based on mark-up differences between variants in the market, which can be used to a priori determine whether a change in market structure would increase or decrease welfare. These results are general to the nested logit model, and the index can thus be used in any market, as long as the market is sufficiently accurately described by the nested logit model. |
| Keywords: | Nested logit model, asymmetry, market structure, welfare indices, emerging technology |
| JEL: | D43 D60 L11 L91 |
| Date: | 2014–10–28 |
| URL: | http://d.repec.org/n?u=RePEc:dgr:uvatin:20140142&r=dcm |
| By: | Salvador Barberà; Alejandro Neme |
| Abstract: | We propose a notion of r-rationality, based on the idea that the choices of individuals are guided by a single preference order, but rather than always choosing the very best available alternative, agents are content with selecting one of the r-best. This proposal provides a purely ordinal and relative version of the classical idea of satisficing behavior. No level of satisfaction is exogenously fixed, agents are not full maximizers, but they follow a clear pattern of behavior whose consequences generate testable implications, which we fully characterize. The notion of r-rationalizability is further extended to individuals whose ordinal satisficing level may vary depending on the set of available alternatives: a similar characterization obtains. Since any choice function F is n-rationalizable, we can ask for the minimal r(F) for which F is r(F) rationalizable, and take that value as a measure of the agent's degree of rationality. We provide an algorithm to compute it for any given F. Special cases of ordinal relative satisficing behavior are shown to result from a variety of choice models proposed in the literature. Our notion allows for further flexibility, yet still provides precise restrictions on observable data. |
| Keywords: | choice, rationality, satisficing behavior, rationazability, preferences, choice functions |
| JEL: | D71 |
| Date: | 2014–10 |
| URL: | http://d.repec.org/n?u=RePEc:bge:wpaper:790&r=dcm |
| By: | Frühwirth-Schnatter, Sylvia (Vienna University of Economics and Business); Pamminger, Christoph (Johannes Kepler University Linz); Weber, Andrea (Universität Mannheim and WIFO); Winter-Ebmer, Rudolf (Johannes Kepler University Linz and IHS) |
| Abstract: | Using Bayesian Markov chain clustering analysis we investigate career paths of Austrian women after their first birth. This data-driven method allows characterizing long-term career paths of mothers over up to 19 years by transitions between parental leave, non-employment and different forms of employment. We, thus, classify women into five cluster-groups with very different long-run career costs of childbearing. We model group membership with a multinomial specification within the finite mixture model. This approach gives insights into the determinants of the long-run family gap. Giving birth late in life may lead very diverse outcomes: on the one hand, it increases the odds to drop out of labor force, and on the other hand, it increases the odds to reach a high-wage career track. |
| Keywords: | Fertility, timing of birth, family gap, Transition Data, Markov Chain Monte Carlo, Multinomial Logit, Panel Data |
| Date: | 2014–10 |
| URL: | http://d.repec.org/n?u=RePEc:ihs:ihsesp:308&r=dcm |