|
on Discrete Choice Models |
| By: | Yusuke Narita (Yale University); Haoge Chang; Kota Saito |
| Abstract: | We obtain a necessary and sufficient condition under which random-coefficient discrete choice models, such as mixed-logit models, are rich enough to approximate any nonparametric random utility models arbitrarily well across choice sets. The condition turns out to be the affine-independence of the set of characteristic vectors. When the condition fails, resulting in some random utility models that cannot be closely approximated, we identify preferences and substitution patterns that are challenging to approximate accurately. We also propose algorithms to quantify the magnitude of approximation errors. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:cwl:cwldpp:2392&r= |
| By: | Nathaniel T. Wilcox |
| Abstract: | Experimental and behavioral economists, as well as psychologists, commonly assume conditional independence of choices when constructing likelihood functions for structural estimation of choice functions. I test this assumption using data from a new experiment designed for this purpose. Within the limits of the experiment’s identifying restriction and designed power to detect deviations from conditional independence, conditional independence is not rejected. In naturally occurring data, concerns about violations of conditional independence are certainly proper and well-taken (for wellknown reasons). However, when an experimenter employs the particular experimental mechanisms and designs used here, the findings suggest that conditional independence is an acceptable assumption for analyzing data so generated. Key Words: Alternation, Conditional Independence, Choice Under Risk, Discrete Choice, Persistence, Random Problem Selection |
| JEL: | C22 C25 C91 D81 |
| Date: | 2024 |
| URL: | http://d.repec.org/n?u=RePEc:apl:wpaper:24-15&r= |
| By: | Drichoutis, Andreas C.; Cerjak, Marija; Kovačić, Damir; Juračak, Josip |
| Abstract: | This study examines consumer preferences for organic and local apples by combining between- and within-subject design characteristics in a second price auction. We first ask subjects to bid for 1 Kg of apples without any information. In subsequent rounds we reveal information about the organic or local attributes of apples and then allow subjects to taste the apples. Results show a significant price premium for the organic attribute (but not for the local attribute) once information is provided while tasting does not further increase elicited willingness-to-pay. We also find that the mixed-subject design results in more accurate willingness-to-pay estimates than when we use information from the between-subjects or within-subjects treatments alone. These results highlight the interplay between different quality attributes in consumer decision making and emphasize the gains that can be achieved by combining between- and within-subjects characteristics in experimental auctions. |
| Keywords: | experimental auctions, second (2nd) price auction, SPA, between-subjects random incentive scheme, BRIS |
| JEL: | C80 C91 D44 |
| Date: | 2024–05–07 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:120880&r= |
| By: | Richard T. Carson; Derrick H. Sun; Yixiao Sun |
| Abstract: | At the core of most random utility models (RUMs) is an individual agent with a random utility component following a largest extreme value Type I (LEVI) distribution. What if, instead, the random component follows its mirror image -- the smallest extreme value Type I (SEVI) distribution? Differences between these specifications, closely tied to the random component's skewness, can be quite profound. For the same preference parameters, the two RUMs, equivalent with only two choice alternatives, diverge progressively as the number of alternatives increases, resulting in substantially different estimates and predictions for key measures, such as elasticities and market shares. The LEVI model imposes the well-known independence-of-irrelevant-alternatives property, while SEVI does not. Instead, the SEVI choice probability for a particular option involves enumerating all subsets that contain this option. The SEVI model, though more complex to estimate, is shown to have computationally tractable closed-form choice probabilities. Much of the paper delves into explicating the properties of the SEVI model and exploring implications of the random component's skewness. Conceptually, the difference between the LEVI and SEVI models centers on whether information, known only to the agent, is more likely to increase or decrease the systematic utility parameterized using observed attributes. LEVI does the former; SEVI the latter. An immediate implication is that if choice is characterized by SEVI random components, then the observed choice is more likely to correspond to the systematic-utility-maximizing choice than if characterized by LEVI. Examining standard empirical examples from different applied areas, we find that the SEVI model outperforms the LEVI model, suggesting the relevance of its inclusion in applied researchers' toolkits. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.08222&r= |
| By: | Klaus Abbink (Monash University); Gaurav Datt (Monash University); Lata Gangadharan (Monash University); Digvijay Negi (Indira Gandhi Institute of Development Research); Bharat Ramaswami (Ashoka University) |
| Abstract: | Are in-kind transfers associated with deadweight losses? To answer this question, we conducted an incentivized field experiment in India and offered low-income respondents the choice between a free quantity of rice and varying amounts of cash to elicit their willingness to pay for rice. Contrary to expectation, we find evidence of deadweight gain on average, though with a striking contrast between a deadweight loss among women from female-headed households and a deadweight gain among women from male-headed households. After investigating alternative mechanisms, our results highlight that greater bargaining power of women within households increases the propensity to choose cash over rice. |
| Keywords: | cash transfer; deadweight loss; field experiment; food subsidy; in-kind transfer |
| Date: | 2024–03–31 |
| URL: | http://d.repec.org/n?u=RePEc:ash:wpaper:110&r= |
| By: | Pawe{\l} Dziewulski; Joshua Lanier; John K. -H. Quah |
| Abstract: | Afriat's Theorem (1967) states that a dataset can be thought of as being generated by a consumer maximizing a continuous and increasing utility function if and only if it is free of revealed preference cycles containing a strict relation. The latter property is often known by its acronym, GARP (for generalized axiom of revealed preference). This paper surveys extensions and applications of Afriat's seminal result. We focus on those results where the consistency of a dataset with the maximization of a utility function satisfying some property can be characterized by a suitably modified version of GARP. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.08459&r= |
| By: | Alyssa Carlson (Department of Economics, University of Missouri-Columbia) |
| Abstract: | Previously, identification of triangular random coefficient models required a restriction on the dimension of the first stage heterogeneity or independence assumptions across the different sources of the heterogeneity. This note proposes a new identification strategy that does not rely on either of these restrictions but rather assumes conditional means have a conditional linear projection representation in order to construct "correction functions" to address endogeneity and gain identification of the average partial effect. This identification strategy allows for both continuous and discrete instruments. Finally, the proposed identification method is illustrated in estimating the returns to education. |
| Keywords: | Endogeneity, Control Function, Random Coefficient, Conditional Linear Projection |
| JEL: | C3 |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:umc:wpaper:2405&r= |
| By: | Junho Choi; Ryo Okui |
| Abstract: | This paper concerns the estimation of linear panel data models with endogenous regressors and a latent group structure in the coefficients. We consider instrumental variables estimation of the group-specific coefficient vector. We show that direct application of the Kmeans algorithm to the generalized method of moments objective function does not yield unique estimates. We newly develop and theoretically justify two-stage estimation methods that apply the Kmeans algorithm to a regression of the dependent variable on predicted values of the endogenous regressors. The results of Monte Carlo simulations demonstrate that two-stage estimation with the first stage modeled using a latent group structure achieves good classification accuracy, even if the true first-stage regression is fully heterogeneous. We apply our estimation methods to revisiting the relationship between income and democracy. |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2405.08687&r= |
| By: | Ammann, Matthias; Puppe, Clemens |
| Abstract: | How can we assess the diversity of a group of decision makers? Identifying decision makers with their preferences, we address this question by applying the multi-attribute approach developed by Nehring and Puppe (2002) to sets of preferences. Specifically, we provide a repertoire of alternative models to measure the diversity of sets of preferences. The proposed models are purely ordinal and are characterized in terms of the different properties that a preference order need to satisfy in order to contribute to the diversity of a given set of preference orderings. |
| Keywords: | Diversity, Committees, Sets of Preferences |
| Date: | 2024 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:kitwps:295730&r= |
| By: | Mihir Bhattacharya (Ashoka University); Ojasvi Khare (Indian Statistical Institute) |
| Abstract: | We consider a social choice model where voters have single-peaked preferences over the alternatives that are aggregated to produce contiguous sets or intervals of fixed cardinality, L. This is applicable in situations where the alternatives can be arranged in a line (e.g. plots of land) and a contiguous subset of these is required (e.g. a hospital or a school). We define interval-social choice correspondences (I-SCCs) on profiles of single-peaked preferences which select intervals. We extend single-peaked preferences to intervals using responsiveness. We show that generalized median-interval (GMI) rules are the only strategy-proof, anonymous and interval efficient I-SCCs. These rules are interval versions of generalized median voter rules which consist of the median, min and max rules. We show that responsiveness over intervals is necessary for the strategy-proofness of the GMI rule if preferences over alternatives are single-peaked. |
| Keywords: | median voter; responsive; single-peaked preferences; social choice correspondence; strategy-proofness; voter |
| Date: | 2023–03–14 |
| URL: | http://d.repec.org/n?u=RePEc:ash:wpaper:89&r= |
| By: | Aidan Coville; Joshua S. Graff Zivin; Arndt Reichert; Ann-Kristin Reitmann |
| Abstract: | Solar technologies have been associated with private and social returns, but their technological potential often remains unachieved because of persistently low demand for high-quality products. In a randomized field experiment in Senegal, we assess the potential of three types of quality signaling to increase demand for high-quality solar lamps. We find no effect on demand when consumers are offered a money-back guarantee but increased demand with a third-party certification or warranty, consistent with the notion that consumers are uncertain about product durability rather than their utility. However, despite the higher willingness to pay, the prices they would pay are still well below market prices for the average household, suggesting that reducing information asymmetries alone is insufficient to encourage wider adoption. Surprisingly, we also find that the effective quality signals in our setting stimulate demand for low-quality products by creating product-class effects among those least familiar with the product. |
| JEL: | D12 D83 L15 O13 Q41 |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:32397&r= |
| By: | Serguei Maliar; Bernard Salanie |
| Abstract: | The positive correlation test for asymmetric information developed by Chiappori and Salanie (2000) has been applied in many insurance markets. Most of the literature focuses on the special case of constant correlation; it also relies on restrictive parametric specifications for the choice of coverage and the occurrence of claims. We relax these restrictions by estimating conditional covariances and correlations using deep learning methods. We test the positive correlation property by using the intersection test of Chernozhukov, Lee, and Rosen (2013) and the "sorted groups" test of Chernozhukov, Demirer, Duflo, and Fernandez-Val (2023). Our results confirm earlier findings that the correlation between risk and coverage is small. Random forests and gradient boosting trees produce similar results to neural networks. |
| Date: | 2024–04 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2404.18207&r= |
| By: | Drichoutis, Andreas C.; Palma, Marco; Feldman, Paul |
| Abstract: | Previous literature analyzing the effects of incentive compatibility of experimental payment mechanisms is dominated by theory. With overwhelming evidence of theory violations in a multiplicity of domains, we fill this gap by empirically exploring the effects of different payment mechanisms in induced preference elicitation using a large sample of over 3800 participants across three experiments. In Experiment 1, we collected responses for offer prices to sell a card like in Cason and Plott (2014), systematically varying on a between-subjects basis the way subjects received payments over repeated rounds, by either paying for all decisions (and various modifications) or just one, as well as making the payments certain, probabilistic or purely hypothetical. While we find that the magnitude of the induced value and the range of the prices used to draw a random price significantly affect misbidding behavior, neither the payment mechanism nor the certainty of payment affected misbidding. In Experiment 2, we replaced the BDM mechanism with a second price auction and found similar results, albeit less misbidding rates. In Experiment 3, we examine the effect of payment mechanisms on choice under risk and find portfolio effects (i.e., paying all rounds) when the lottery pairs do not involve options with certainty. Overall, our empirical exercise shows that payment mechanism design considerations should place more weight on the choice architecture rather than on incentive compatibility. |
| Keywords: | Becker-DeGroot-Marschak mechanism, second price auction, risk choices, preference elicitation, choice architecture |
| JEL: | C80 C91 D44 |
| Date: | 2024–05–08 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:120898&r= |
| By: | Olivier Armantier; Sebastian Doerr; Jon Frost; Andreas Fuster; Kelly Shue |
| Abstract: | Many digital applications rely on the willingness of users to voluntarily share personal data. Yet some users are more comfortable sharing data than others. To document these differences, we draw on questions to a representative sample of U.S. households added to the New York Fed's Survey of Consumer Expectations. We find that women a re less willing than men, and older individuals less willing than the young, to share their financial transaction data in exchange for better offers on financial services. Across these groups, there are significant differences in attitudes, such as willingness to take financial risks, concerns that data will become publicly available, and concerns around personal safety. Responses suggest that privacy regulation can increase the willingness to share data, but effects do not differ by gender. |
| Keywords: | data, privacy, CCPA, fintech, big tech, survey of consumer expectations |
| JEL: | C8 D8 |
| Date: | 2024–05 |
| URL: | http://d.repec.org/n?u=RePEc:bis:biswps:1187&r= |