|
on Discrete Choice Models |
| By: | Chris Muris; Cavit Pakel; Qichen Zhang |
| Abstract: | We consider ordered logit models for directed network data that allow for flexible sender and receiver fixed effects that can vary arbitrarily across outcome categories. This structure poses a significant incidental parameter problem, particularly challenging under network sparsity or when some outcome categories are rare. We develop the first estimation method for this setting by extending tetrad-differencing conditional maximum likelihood (CML) techniques from binary choice network models. This approach yields conditional probabilities free of the fixed effects, enabling consistent estimation even under sparsity. Applying the CML principle to ordered data yields multiple likelihood contributions corresponding to different outcome thresholds. We propose and analyze two distinct estimators based on aggregating these contributions: an Equally-Weighted Tetrad Logit Estimator (ETLE) and a Pooled Tetrad Logit Estimator (PTLE). We prove PTLE is consistent under weaker identification conditions, requiring only sufficient information when pooling across categories, rather than sufficient information in each category. Monte Carlo simulations confirm the theoretical preference for PTLE, and an empirical application to friendship networks among Dutch university students demonstrates the method's value. Our approach reveals significant positive homophily effects for gender, smoking behavior, and academic program similarities, while standard methods without fixed effects produce counterintuitive results. |
| Date: | 2025–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2507.16689 |
| By: | Christoph Engel (Max Planck Institute for Research on Collective Goods, Bonn) |
| Abstract: | In an experiment on the large language model GPT-4o, a supplier always makes a higher profit if it replaces uniform contract terms with a set of terms between which the custom-er may choose. The extra profit results from price discrimination. There is a first order and a second order effect. The first order effect results from heterogeneous willingness to pay for a more protective term. The second order effect results from the possibility that con-tract choice is a signal for general willingness to pay for the traded commodity. In the ex-periment, the effect is bigger if the least protective version is labelled as the default, and more protective terms as an “upgrade†. The effect is smaller if, conversely, the most pro-tective version is labelled as the default and less protective (and cheaper) versions as an opportunity for “savings†. The effect is also bigger if the supplier only sets the price after it knows which version of the contract the consumer chooses. The profit increasing effect of giving the consumer a choice is strong. There is no piece of demographic information that has a stronger effect. Most pieces of demographic information (which the supplier might, for instance, learn through cookie data) have a significantly smaller effect on profit. If the supplier combines cookie information about demographic markers with contract choice, it always makes an extra profit. |
| Keywords: | forced choice of contract clause; price discrimination; large language model; experiment |
| JEL: | C91 D01 D02 D12 D42 D91 K12 |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:mpg:wpaper:2024_19 |
| By: | Maria A. Cattaneo; Christian Gschwendt; Stefan C. Wolter |
| Abstract: | The global rise in tertiary educational attainment has been attributed to various factors, most commonly higher expected earnings, improved protection against technological change, and prospects for upward social mobility. In a large-scale discrete-choice experiment with nearly 6, 000 adults, we show that when these three factors are held constant, individuals show on average no additional intrinsic willingness to pay (WTP) for a university degree. Individuals are willing to forgo an amount of income roughly equivalent to the total cost of obtaining a university degree - including opportunity and direct costs-when trading off such a degree against basic vocational education. However, we observe significant heterogeneity depending on respondents' own educational attainment, gender and type of tertiary education: individuals with tertiary qualifications and men assign a higher value to higher education and the WTP is higher for university of applied degrees compared to academic university degrees. |
| Keywords: | University, discrete choice experiment, willingness to pay, Switzerland |
| JEL: | I21 I23 I26 |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:iso:educat:0247 |
| By: | Nicolas L. Bottan; Ricardo Perez-Truglia; Hitoshi Shigeoka; Katsunori Yamada |
| Abstract: | Preferences for status are typically attributed to two distinct channels: self-image, in which individuals derive utility from being richer than others, and social-image, in which individuals value being seen as richer by others. While both channels are believed to be at play, little is known about their relative importance. We address this gap using a hypothetical discrete choice experiment. Our findings indicate that self-image is at most 19.3% as important as social-image. Additionally, we document substantial heterogeneity in the strength of these preferences across individuals and domains. |
| JEL: | C9 Z13 |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:34094 |
| By: | Federico Echenique; Alireza Fallah; Michael I. Jordan |
| Abstract: | We propose a general methodology for recovering preference parameters from data on choices and response times. Our methods yield estimates with fast ($1/n$ for $n$ data points) convergence rates when specialized to the popular Drift Diffusion Model (DDM), but are broadly applicable to generalizations of the DDM as well as to alternative models of decision making that make use of response time data. The paper develops an empirical application to an experiment on intertemporal choice, showing that the use of response times delivers predictive accuracy and matters for the estimation of economically relevant parameters. |
| Date: | 2025–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2507.20403 |
| By: | Yu Hao; Hiroyuki Kasahara; Katsumi Shimotsu |
| Abstract: | This paper investigates how the discount factor and payoff functions can be identified in stationary infinite-horizon dynamic discrete choice models. In single-agent models, we show that common nonparametric assumptions on per-period payoffs -- such as homogeneity of degree one, monotonicity, concavity, zero cross-differences, and complementarity -- provide identifying restrictions on the discount factor. These restrictions take the form of polynomial equalities and inequalities with degrees bounded by the cardinality of the state space. These restrictions also identify payoff functions under standard normalization at one action. In dynamic game models, we show that firm-specific discount factors can be identified using assumptions such as irrelevance of other firms' lagged actions, exchangeability, and the independence of adjustment costs from other firms' actions. Our results demonstrate that widely used nonparametric assumptions in economic analysis can provide substantial identifying power in dynamic structural models. |
| Date: | 2025–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2507.19814 |
| By: | Chowdhury, Shyamal (Australian National University); Puente-Beccar, Manuela (Max Planck Institute for Research on Collective Goods); Schildberg-Hörisch, Hannah (Heinrich Heine University Düsseldorf); Schneider, Sebastian O. (Max Planck Institute for Research on Collective Goods); Sutter, Matthias (Max Planck Institute for Research on Collective Goods) |
| Abstract: | We investigate how strongly the local environment beyond the family can contribute to understanding the formation of children's economic preferences. Building on precise geolocation data for around 6.000 children, we use fixed effects, spatial autoregressive models and Kriging to capture the relation between the local environment and children's preferences. The spatial models explain a considerable part of so far unexplained variation in preferences. Moreover, the "spatial stability" of preferences exceeds the village level. Our results highlight the importance of the local environment for the formation of children's preferences, which we quantify to be as large as that of parental preferences. |
| Keywords: | prosociality, risk attitudes, patience, local environment, Kriging, spatial models, skill formation, experiments with children, Bangladesh |
| JEL: | D01 C21 C99 |
| Date: | 2025–07 |
| URL: | https://d.repec.org/n?u=RePEc:iza:izadps:dp18015 |
| By: | Anthony Wiskich |
| Abstract: | This paper investigates the potential long-run effects of autonomous and electric vehicles, and a carbon tax, on personal domestic aviation demand in Australia. We estimate a discrete choice disutility model with two travel modes – car and air – using Australian National Visitor Survey data and Bayesian priors. We use multiplicative Fréchet errors, consistent with a constant elasticity of substitution utility function for a representative consumer of both modes. An elasticity of substitution of almost 4 replicates the observed transition to air travel as distances increase. Combining in turn electrification, autonomy, the use of overnight robotaxis, a 10 kph increase in average car speeds, and an AUS$200/tCO2e carbon tax leads to air passenger reductions of 5%, 19%, 22%, 28% and 43%, respectively. Reductions are highest for shorter flights, so aggregate emissions do not decline as much as passenger numbers, while the number of aircraft trips declines more. |
| Keywords: | aviation economics, autonomous vehicles, decarbonisation, discrete choice travel model |
| JEL: | O33 Q40 Q54 R40 |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:een:camaaa:2025-48 |
| By: | Yuta Kuroda; Takeru Sugasawa |
| Abstract: | This study uses two-stage hedonic estimation to examine household preferences for scattered greenery (e.g., roadside trees and yard bushes) in highly developed urban areas. We use proprietary survey data to obtain a wealth of property and resident characteristics and link these to scattered greenery based on high-resolution satellite images and surrounding amenity characteristics for analysis. The results showed that the preferences for scattered greenery were highly heterogeneous and that a few households were willing to pay a hefty amount. The average household pays about 1, 540 yen per month for scattered greenery if they live on their owned property and about 300 yen per month if they live on rented property. Also, regardless of the type of residence, wealthy people prefer scattered greenery, while those who plan to move within a few years tend to like it less. Additionally, even if they live on an owned property, single households have little willingness to pay for greenery, and even if they live on a rented property, people with a high level of health awareness or people living with children have a high willingness to pay. The results of this study shed light on the causes of heterogeneity in preferences for greenery by decomposing the property and resident characteristics that have been confused in previous studies. |
| Date: | 2025–08–07 |
| URL: | https://d.repec.org/n?u=RePEc:toh:dssraa:148 |
| By: | Matthew A. Tarduno; Reed Walker |
| Abstract: | This paper explores whether misperceptions about air pollution contribute to environmental inequality in the United States. We use a two-part survey experiment to elicit respondents' beliefs about local air quality and pollution's effects on life expectancy. We document how misperception differs across demographic groups and then how this misperception affects willingness to pay (WTP) for cleaner air. Since misperception or beliefs may be correlated with other unobservable determinants of WTP, we randomly show selected participants customized information about their actual air pollution. This allows us to trace out how experimentally induced changes in beliefs affect WTP for air quality. Our results suggest significant misperceptions about air pollution in the US. Respondents, on average, overestimate both their air pollution exposure and its impact on life expectancy. Beliefs about relative air pollution are not systematically biased but are noisy. Despite some differences in misperceptions between Black and White respondents, counterfactual exercises do not suggest that rectifying these misperceptions would meaningfully close the observed gap in WTP and/or pollution exposure. |
| JEL: | H4 Q5 |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:34116 |
| By: | Daniel Engler (University of Kassel, Institute of Economics); Marvin Gleue (University of Kassel, Institute of Economics); Gunnar Gutsche (Paderborn University, Faculty of Business Administration and Economics); Gerrit Hornung (University of Kassel, Institute of Business Law); Sophia Möller (University of Kassel, Institute of Economics); Sabrina Schomberg (University of Kassel, Institute of Business Law); Andreas Ziegler (University of Kassel, Institute of Economics) |
| Abstract: | Inspired by the controversial public and political debate in the European Union (EU) about legal initiatives to protect human rights and the environment along supply chains (e.g., the Corporate Sustainability Due Diligence Directive, CSDDD), this paper examines individual preferences for different designs of supply chain laws that are stricter than the current national legislation. Our econometric analysis is based on data from a representative online survey of 507 citizens in Germany that especially included a stated choice experiment. Our estimation results show that individuals in Germany, on average, have a significantly positive preference for stricter supply chain laws compared to the existing national Supply Chain Act. In addition, the majority of the respondents expect positive sustainability impacts of supply chain laws, while there is ambiguity in the perceptions of whether the economic consequences are predominantly negative. With respect to political attitudes, our results show that citizens with a social or ecological political identification have significantly stronger preferences for stricter supply chain laws. However, in contrast to the strong opposition of conservative and liberal parties in Germany to stricter supply chain legislation, individuals with a liberal or conservative political identification do not have significantly different preferences for stricter supply chain laws than their counterparts. Our results therefore suggest that the political blockade of supply chain laws does not correspond to the views of the majority of the population in Germany. |
| Keywords: | Supply chain laws, individual preferences, stated choice experiment |
| JEL: | K23 K32 K38 Q56 Q58 |
| Date: | 2025 |
| URL: | https://d.repec.org/n?u=RePEc:mar:magkse:202509 |
| By: | Joel L. Horowitz; Sokbae Lee |
| Abstract: | This paper presents a computationally efficient method for binary classification using Manski's (1975, 1985) maximum score model when covariates are discretely distributed and parameters are partially but not point identified. We establish conditions under which it is minimax optimal to allow for either non-classification or random classification and derive finite-sample and asymptotic lower bounds on the probability of correct classification. We also describe an extension of our method to continuous covariates. Our approach avoids the computational difficulty of maximum score estimation by reformulating the problem as two linear programs. Compared to parametric and nonparametric methods, our method balances extrapolation ability with minimal distributional assumptions. Monte Carlo simulations and empirical applications demonstrate its effectiveness and practical relevance. |
| Date: | 2025–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2507.19654 |
| By: | Ismaël Rafaï (GREDEG - Groupe de Recherche en Droit, Economie et Gestion - UNS - Université Nice Sophia Antipolis (1965 - 2019) - CNRS - Centre National de la Recherche Scientifique - UniCA - Université Côte d'Azur); Bérengère Davin-Casalena (ORS PACA - Observatoire régional de la santé Provence-Alpes-Côte d'Azur [Marseille]); Dimitri Dubois (CEE-M - Centre d'Economie de l'Environnement - Montpellier - CNRS - Centre National de la Recherche Scientifique - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement - Institut Agro Montpellier - Institut Agro - Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement - UM - Université de Montpellier); Thierry Blayac (CEE-M - Centre d'Economie de l'Environnement - Montpellier - CNRS - Centre National de la Recherche Scientifique - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement - Institut Agro Montpellier - Institut Agro - Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement - UM - Université de Montpellier); Bruno Ventelou (AMSE - Aix-Marseille Sciences Economiques - EHESS - École des hautes études en sciences sociales - AMU - Aix Marseille Université - ECM - École Centrale de Marseille - CNRS - Centre National de la Recherche Scientifique) |
| Abstract: | Recent advances in artificial intelligence (AI) have made it possible to detect neurodegenerative diseases (NDDs) earlier, potentially improving patient outcomes. However, AI-based detection tools remain underutilized. We studied individual valuation for early diagnosis tests for NDDs. We conducted a discrete choice experiment with a representative sample of the French adult population (N = 1017). Participants were asked to choose between early diagnosis tests that differed in terms of: (1) type of test (saliva vs. AI-based tests analysing electronic health records); (2) identity of the person communicating the test results; (3) sensitivity; (4) specificity; and (5) price. We calculated the weights in the decision for each attribute and examined how socio-demographic characteristics influenced them. Respondents revealed a reduced utility value when AI-based testing was involved (valuated at an average of €36.08, CI [€22.13; €50.89]) and when results were communicated by a private company (€95.15, CI [€82.01; €109.82]). We interpret these figures as the shadow price that the public attaches to medical data privacy. Beyond monetization, our representative sample of the French population appears reluctant to adopt AI-powered screening, particularly when performed on large sets of personal data. However, they would be more supportive when medical expertise is associated with the tests. |
| Date: | 2025–07–23 |
| URL: | https://d.repec.org/n?u=RePEc:hal:journl:hal-05189620 |
| By: | Johannes Gessner; Andreas Gerster; Michael Kramm |
| Abstract: | There is growing evidence that households often forgo profitable energy efficiency retrofits, partly due to inattention and imperfect information about their economic benefits. We conduct an incentivized survey experiment to evaluate both the effecƟveness and the welfare implicaƟons of a widely used policy tool aimed at addressing this issue: providing information from an energy efficiency audit. In our incentivized experiment, participants in the treatment group receive personalized information about the potential cost savings from retrofitting their heating systems, while those in the control group do not receive such information. Our results show that providing this information does not increase the average willingness to pay for a retrofit. |
| Keywords: | information provision, nudge, welfare, heterogeneity, incentivized survey experiment, energy efficiency |
| JEL: | C93 D83 Q41 Q48 |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:bon:boncrc:crctr224_2025_696 |
| By: | Seolah Kim (California State University, Los Angeles); Michael Bates (University of California, Riverside) |
| Abstract: | We propose a per-cluster instrumental-variables approach (PCIV) for estimating correlated random coefficient models in the presence of contemporaneous endogeneity and two- way fixed effects using Stata. Our estimator uses variation across clusters to estimate coefficients with homogeneous slopes (such as time effects) and within-cluster variation to estimate the cluster-specific heterogeneity. We aggregate cluster-specific estimates to population averages. We demonstrate consistency, showing robustness over standard estimators, and provide analytic standard errors for robust inference. Our Stata package allows for straightforward implementation. In Monte Carlo simulation, PCIV performs relatively well against pooled 2SLS and fixed-effects IV (FEIV) with a finite number of clusters or finite observations per cluster. We apply PCIV in estimating the price elasticity of gasoline demand using state fuel taxes as instrumental variables. PCIV estimation allows for greater transparency of the underlying data. It produces graphs depicting divergence in the implicit weighting when applying FEIV from the natural weights applied in PCIV and evidence of correlations between heterogeneity in the first and second stages, violating a key assumption underpinning the consistency of standard estimators. In our application, overlooking effect heterogeneity with standard estimators is consequential. Our estimated distribution of elasticities reveals significant heterogeneity and meaningful differences in estimated averages. |
| Date: | 2025–08–08 |
| URL: | https://d.repec.org/n?u=RePEc:boc:usug25:09 |
| By: | Rebecca Raciborski (US Department of Veterans Affairs); Rafal Raciborski (Michelin North America); Jacob T. Painter (US Department of Veterans Affairs); J. Silas Williams (US Department of Veterans Affairs); Chenghui Li (US Department of Veterans Affairs); Jeffrey Pyne (US Department of Veterans Affairs) |
| Abstract: | Cost-effectiveness analysis (CEA) is often conducted alongside a randomized clinical trial to establish whether the new therapy is likely to have a favorable value for its cost. One common approach is to estimate an incremental cost-effectiveness ratio (ICER), the marginal health benefit relative to the marginal cost, and compare the point estimate with a prespecified “willingness to pay”. Alternatively, net monetary benefit (NMB) may be used to keep benefits and costs linear and on the same scale. Costs and benefits may be modeled separately and often assume different distributions, especially for the ICER, where benefits are generally constrained to the -1 to 1 interval. CEA also involves use of graphs to assess uncertainty about the decision being made. The first, the cost-effectiveness plane, plots bootstrapped replicates of incremental cost against incremental benefits with confidence ellipses. The second, the cost-effectiveness acceptability curve (CEAC), is a plot showing the probability that a new treatment will be cost-effective at different willingness-to-pay values. In this presentation, we will introduce a new suite of Stata CEA commands. They use standard Stata command syntax to fit models and obtain the ICER or NMB and then provide comprehensive postestimation support and graphing. |
| Date: | 2025–08–08 |
| URL: | https://d.repec.org/n?u=RePEc:boc:usug25:10 |
| By: | Antonia Antweiler; Joachim Freyberger |
| Abstract: | This paper examines estimation of skill formation models, a critical component in understanding human capital development and its effects on individual outcomes. Existing estimators are either based on moment conditions and only applicable in specific settings or rely on distributional approximations that often do not align with the model. Our method employs an iterative likelihood-based procedure, which flexibly estimates latent variable distributions and recursively incorporates model restrictions across time periods. This approach reduces computational complexity while accommodating nonlinear production functions and measurement systems. Inference can be based on a bootstrap procedure that does not require re-estimating the model for bootstrap samples. Monte Carlo simulations and an empirical application demonstrate that our estimator outperforms existing methods, whose estimators can be substantially biased or noisy. |
| Date: | 2025–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2507.18995 |
| By: | Ke Wang; Dongmin Yao; Xin Ye; Mingyang Pei |
| Abstract: | While ride-hailing services offer increased travel flexibility and convenience, persistent nighttime safety concerns significantly reduce women's willingness to use them. Existing research often treats women as a homogeneous group, neglecting the heterogeneity in their decision-making processes. To address this gap, this study develops the Latent Class Integrated Choice and Latent Variable (LC-ICLV) model with a mixed Logit kernel, combined with an ordered Probit model for attitudinal indicators, to capture unobserved heterogeneity in women's nighttime ride-hailing decisions. Based on panel data from 543 respondents across 29 provinces in China, the analysis identifies two distinct female subgroups. The first, labeled the "Attribute-Sensitive Group", consists mainly of young women and students from first- and second-tier cities. Their choices are primarily influenced by observable service attributes such as price and waiting time, but they exhibit reduced usage intention when matched with female drivers, possibly reflecting deeper safety heuristics. The second, the "Perception-Sensitive Group", includes older working women and residents of less urbanized areas. Their decisions are shaped by perceived risk and safety concerns; notably, high-frequency use or essential nighttime commuting needs may reinforce rather than alleviate avoidance behaviors. The findings underscore the need for differentiated strategies: platforms should tailor safety features and user interfaces by subgroup, policymakers must develop targeted interventions, and female users can benefit from more personalized risk mitigation strategies. This study offers empirical evidence to advance gender-responsive mobility policy and improve the inclusivity of ride-hailing services in urban nighttime contexts. |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2508.10951 |