|
on Discrete Choice Models |
| By: | Mogens Fosgerau (Department of Economics, Copenhagen University); Emerson Melo (Indiana University Bloomington); André de Palma (Ecole Normale Superieure de Cachan (ENS)); Matthew Shum (California Institute of Technology) |
| Abstract: | This paper establishes a general equivalence between discrete choice and rational inattention models. Matejka and McKay (2015, AER) showed that when information costs are modelled using the Shannon entropy, the resulting choice probabilities in the rational inattention model take the multinomial logit form. We show that when information costs are modelled using a class of generalized entropies, then the choice probabilities in any rational inattention model are observationally equivalent to some additive random utility discrete choice model and vice versa. This equivalence arises from convex- analytic properties of the random utility model. Thus any additive random utility model can be given an interpretation in terms of boundedly rational behavior. We provide examples of this equivalence utilizing the nested logit model, an empirically relevant random utility model allowing for flexible substitution possibilities between choices. |
| Keywords: | Rational Inattention, Discrete Choice, Random Utility, General Entropy, Convex Analysis |
| JEL: | D03 C25 D81 |
| Date: | 2017–12–06 |
| URL: | http://d.repec.org/n?u=RePEc:kud:kuiedp:1726&r=dcm |
| By: | Vincenzina Caputo (Michigan State University); Riccardo Scarpa (University of Waikato); Rodlofo M. Nayga (University of Arkansas); David L. Ortega (Michigan State University) |
| Abstract: | We empirically question the commonly employed distributional assumption of normality of taste distribution in mixed logit models with continuous random parameters. We use a WTP-space random utility discrete choice model with flexible distributions (Train 2016) on data from two choice experiments regarding beef with nested set of quality attributes. We specifically address distributional features such as asymmetry, multi-modality and range of variation, and find little support for normality. Our results are robust to attribute dimensionality in experimental design. Implications of our results for practitioners in the field are discussed. |
| Keywords: | flexible taste distributions; mixed logit; logit mixed logit; food preferences; preference heterogneity |
| Date: | 2017–11–30 |
| URL: | http://d.repec.org/n?u=RePEc:wai:econwp:17/27&r=dcm |
| By: | Jason Abaluck (Institute for Fiscal Studies); Abi Adams (Institute for Fiscal Studies and University of Oxford) |
| Abstract: | Consideration set models relax the assumption that consumers are aware of all available options. Thus far, identification arguments for these models have relied either on auxiliary data on what options were considered or on instruments excluded from consideration or utility. In a discrete choice framework subsuming logit, probit and random coefficients models, we prove that utility and consideration set probabilities can be separately identified without these data intensive methods. In full-consideration models, choice probabilities satisfy a symmetry property analogous to Slutsky symmetry in continuous choice models. This symmetry breaks down in consideration set models when changes in characteristics perturb consideration, and we show that consideration probabilities are constructively identified from the resulting asymmetries. In a lab experiment, we recover preferences and consideration probabilities using only data on which items were ultimately chosen, and we apply the model to study hotel choices on Expedia.com and insurance choices in Medicare Part D. |
| Keywords: | Asymmetric demand responses, consumers |
| Date: | 2017–07–07 |
| URL: | http://d.repec.org/n?u=RePEc:ifs:ifsewp:17/09&r=dcm |
| By: | O. Ashton Morgan; William L.Huth; Paul Hindsley |
| Abstract: | Recent research examining voting behavior in contingent valuation referenda informs on how consequential survey respondents behave and its impact on willingness to pay values."This research attempts to examine whether this behavior holds across population subgroups. We consider resident and non-resident users of artificial reefs and find improved construct validity for our resident models over non-resident models. Specifically, resident behavior is in line with a priori expectations with consequential residents more likely to vote in favor of a policy for additional reef funding – a result that is consistent with the “protest no” literature. Consequently, consequential resident voters exhibit a greater willingness to pay than inconsequential voters. Non-resident behavior differs, however. For this subgroup, consequentiality does not influence voting behavior and willingness-to-pay values do not differ by consequentiality. Overall, more work is required to appropriately identify willingness to pay values for non-resident populations, particularly from a benefit-cost perspective, where appropriately identifying subgroup WTP values are a critical component of measuring the net present value of a given policy. Key Words: |
| Date: | 2017 |
| URL: | http://d.repec.org/n?u=RePEc:apl:wpaper:17-10&r=dcm |
| By: | Goytom Abraha Kahsay (Department of Food and Resource Economics, University of Copenhagen); Workineh Asmare Kassie (School of Economics, University of Gondar); Abebe Damte Beyene (Environment and Climate Research Center (ECRC), Ethiopian Development Research Institute (EDRI)); Lars Gårn Hansen (Department of Food and Resource Economics, University of Copenhagen) |
| Abstract: | The Ethiopian food for work program typically induces forest conservation work. While economic outcomes have been studied before, little is known about the program’s environmental impact. We run a choice experiment among Ethiopian farmers eliciting preferences in a hypothetical afforestation program that mimics the Ethiopian food-for-work program. We find that introducing food incentives decreases willingness to participate in the program and participation rate increases with an increase in the proportion of individuals selected for food incentive. We also find that the crowding-out effect is stronger when food incentive recipients are selected based on income compared to lottery-based selection. Our data points to pro-social signaling as the most likely channel for the crowding-out effect. These results suggest that (1) food-for-work programs could have unintended negative environmental effects and (2) directions for design reform that could mitigate this. |
| Keywords: | Crowding-out; Food-for-work program, Pro-environmental behavior; Selection; Pro-social signaling |
| JEL: | D03 D64 D82 Q57 |
| Date: | 2017–12 |
| URL: | http://d.repec.org/n?u=RePEc:foi:wpaper:2017_13&r=dcm |
| By: | Bergantino, Angela Stefania; Madio, Leonardo |
| Abstract: | We study the demand and the willingness-to-pay for a new High-Speed (HSR) line on the Bari-Rome route, and its indirect effect on the connected Brindisi-Rome line, when competing with other existing transport modes. We carry out a discrete choice experiment over a significant number of respondents. We find that reductions in access and egress (A/E) time are more valued than in-vehicle travel time if HSR is available (faster services) while, when only traditional services are available, the opposite is true. This confirms that fragmented journeys, for faster connections, yield greater disutility and this would be the greater competitive advantage of HSR services. We also explore the heterogeneity among respondents, by studying the relationship between in-vehicle, and A/E travel time considering different population segments, i.e. different income levels, travel habits (frequent or occasional), and travel purposes, in order to profile potential users. We also study the patterns of the inter-modal substitutability. We find that increasing the travel distance by 120 km (to Brindisi) still guarantees large substitution between HSR and air transport mode. |
| Date: | 2017 |
| URL: | http://d.repec.org/n?u=RePEc:sit:wpaper:17_6&r=dcm |
| By: | Dino Borie (GREDEG - Groupe de Recherche en Droit, Economie et Gestion - CNRS - Centre National de la Recherche Scientifique - UNS - Université Nice Sophia Antipolis - UCA - Université Côte d'Azur - UCA - Université Côte d'Azur); Dorian Jullien (GREDEG - Groupe de Recherche en Droit, Economie et Gestion - CNRS - Centre National de la Recherche Scientifique - UNS - Université Nice Sophia Antipolis - UCA - Université Côte d'Azur - UCA - Université Côte d'Azur) |
| Abstract: | The standard model of choice behavior relies on an implicit assumption that a decision maker is not affected by different descriptions of a given problem (description invariance). However, the behavioral economics and psychology literatures provide well-established evidence that descriptions do in fact influence decision makers. In this paper, we distinguish between descriptions of objects of choice and consequences of objects of choice in order to deduce a decision maker's preferences over the descriptions from observed choices over the consequences. We provide a choice theoretical foundation for maximizing preference relations subject to the class of framing effects where description invariance is violated. JEL Classification: D89, D90, D91. |
| Keywords: | Choice correspondence,framing effects,rational choice,description invariance,description dependence |
| Date: | 2017–11–28 |
| URL: | http://d.repec.org/n?u=RePEc:hal:wpaper:halshs-01651086&r=dcm |