|
on Discrete Choice Models |
| By: | Felix Aidala; Gizem Koşar; Daniel Mangrum; Wilbert Van der Klaauw |
| Abstract: | Consumer demand for “Buy Now, Pay Later” (BNPL) has surged, but the specific attributes consumers value remain unclear. We conduct a novel probabilistic stated choice experiment varying BNPL attributes across hypothetical scenarios to estimate consumers’ underlying preferences and their willingness to pay (WTP) for each feature. Consumers have a negative WTP for the standard bundle, on average, but younger and lower income consumers have stronger demand. Simulating consumer demand with estimated preference parameters reveals that most shifts away from the standard BNPL bundle reduce demand and create a more negatively selected pool of BNPL users, especially when interest is charged. |
| Keywords: | Buy Now Pay Later (BNPL); payment services; financial inclusion; probabilistic stated choices; survey experiment |
| JEL: | G51 G41 C93 R22 |
| Date: | 2025–10–01 |
| URL: | https://d.repec.org/n?u=RePEc:fip:fednsr:101928 |
| By: | Deschacht, Nick (KU Leuven); Guillemyn, Inés (University of Antwerp); Vujic, Suncica (University of Antwerp) |
| Abstract: | This study estimates individuals’ willingness to pay for pension benefits using a discrete choice experiment with fictitious job advertisements conducted among workers in the United Kingdom (UK). The results indicate that workers are willing to trade off current pay for additional pension benefits, with the marginal worker willing to forgo 0.3% of their current wage for a one percentage point increase in pension benefits. Willingness to pay varies significantly across individuals, increasing with proximity to retirement age, higher income levels, financial planning and financial literacy. |
| Keywords: | discrete choice experiment (DCE), wage-pension trade-off, United Kingdom |
| JEL: | C9 D9 J16 J32 |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:iza:izadps:dp18164 |
| By: | Daniel P\'erez-Troncoso |
| Abstract: | Discrete Choice Experiments (DCEs) are widely used to elicit preferences for products or services by analyzing choices among alternatives described by their attributes. The quality of the insights obtained from a DCE heavily depends on the properties of its experimental design. While early DCEs often relied on linear criteria such as orthogonality, these approaches were later found to be inappropriate for discrete choice models, which are inherently non-linear. As a result, statistically efficient design methods, based on minimizing the D-error to reduce parameter variance, have become the standard. Although such methods are implemented in several commercial tools, researchers seeking free and accessible solutions often face limitations. This paper presents DCEtool, an R package with a Shiny-based graphical interface designed to support both novice and experienced users in constructing, decoding, and analyzing statistically efficient DCE designs. DCEtool facilitates the implementation of serial DCEs, offers flexible design settings, and enables rapid estimation of discrete choice models. By making advanced design techniques more accessible, DCEtool contributes to the broader adoption of rigorous experimental practices in choice modelling. |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2509.15326 |
| By: | Syngjoo Choi; Bongseop Kim; Young-Sik Kim; Ohik Kwon; Soeun Park |
| Abstract: | To overcome the lack of data in predicting the payment preference for central bank digital currency (CBDC), we conducted a discrete choice experiment that varied the attributes of payment methods among over 3, 500 participants in Korea. We identified key attributes, such as the discount rate and the issuance form, that shape the demand for payment methods. The predicted usage shares of existing payment methods closely align with their actual usage patterns in Korea, which lends credible support for the external validity of our experimental design. Building on this validation, we further predict that CBDC, when introduced, will be preferred over cash and mobile fast payment but less preferred than credit and debit cards, with its adoption rate as the most preferred payment method ranging 19−27% of respondents. |
| Keywords: | payment preference, retail CBDC, discrete choice experiment |
| JEL: | E40 E50 C90 |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:bis:biswps:1296 |
| By: | Enrico G. De Giorgi (University of St. Gallen - SEPS: Economics and Political Sciences; Swiss Finance Institute); Thierry Post (Graduate School of Business of Nazarbayev University); Askhat Omar (Nazarbayev University - Graduate School of Business) |
| Abstract: | We present experimental evidence of systematic decision errors in dynamic portfolio choice. Participants created contingency plans in a lattice model. When returns were independent and identically distributed, most plans were near-optimal for plausible risk preferences. However, under dynamic probabilities, most plans were inefficient, even by First-degree Stochastic Dominance. Allocations showed a lack of sensitivity to probability shifts, consistent with myopic loss aversion. Decision quality improved when participants compared their original plan to precomputed optimal plans. Results highlight the importance of problem framing in dynamic choice and support a libertarian paternalistic approach to choice architecture design. |
| Keywords: | Dynamic portfolio choice, choice experiments, myopic loss aversion |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:chf:rpseri:rp2578 |
| By: | Onil Boussim |
| Abstract: | In difference-in-differences (DiD) settings with categorical outcomes, treatment effects often operate on both total quantities (e.g., voter turnout) and category shares (e.g., vote distribution across parties). In this context, linear DiD models can be problematic: they suffer from scale dependence, may produce negative counterfactual quantities, and are inconsistent with discrete choice theory. We propose compositional DiD (CoDiD), a new method that identifies counterfactual categorical quantities, and thus total levels and shares, under a parallel growths assumption. The assumption states that, absent treatment, each category's size grows or shrinks at the same proportional rate in treated and control groups. In a random utility framework, we show that this implies parallel evolution of relative preferences between any pair of categories. Analytically, we show that it also means the shares are reallocated in the same way in both groups in the absence of treatment. Finally, geometrically, it corresponds to parallel trajectories (or movements) of probability mass functions of the two groups in the probability simplex under Aitchison geometry. We extend CoDiD to i) derive bounds under relaxed assumptions, ii) handle staggered adoption, and iii) propose a synthetic DiD analog. We illustrate the method's empirical relevance through two applications: first, we examine how early voting reforms affect voter choice in U.S. presidential elections; second, we analyze how the Regional Greenhouse Gas Initiative (RGGI) affected the composition of electricity generation across sources such as coal, natural gas, nuclear, and renewables. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.11659 |
| By: | Chris Muris; Cavit Pakel |
| Abstract: | We study estimation and inference for triadic link formation with dyad-level fixed effects in a nonlinear binary choice logit framework. Dyad-level effects provide a richer and more realistic representation of heterogeneity across pairs of dimensions (e.g. importer-exporter, importer-product, exporter-product), yet their sheer number creates a severe incidental parameter problem. We propose a novel ``hexad logit'' estimator and establish its consistency and asymptotic normality. Identification is achieved through a conditional likelihood approach that eliminates the fixed effects by conditioning on sufficient statistics, in the form of hexads -- wirings that involve two nodes from each part of the network. Our central finding is that dyad-level heterogeneity fundamentally changes how information accumulates. Unlike under node-level heterogeneity, where informative wirings automatically grow with link formation, under dyad-level heterogeneity the network may generate infinitely many links yet asymptotically zero informative wirings. We derive explicit sparsity thresholds that determine when consistency holds and when asymptotic normality is attainable. These results have important practical implications, as they reveal that there is a limit to how granular or disaggregate a dataset one can employ under dyad-level heterogeneity. |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2509.26420 |
| By: | Undral Byambadalai; Tomu Hirata; Tatsushi Oka; Shota Yasui |
| Abstract: | We study the estimation of distributional treatment effects in randomized experiments with imperfect compliance. When participants do not adhere to their assigned treatments, we leverage treatment assignment as an instrumental variable to identify the local distributional treatment effect-the difference in outcome distributions between treatment and control groups for the subpopulation of compliers. We propose a regression-adjusted estimator based on a distribution regression framework with Neyman-orthogonal moment conditions, enabling robustness and flexibility with high-dimensional covariates. Our approach accommodates continuous, discrete, and mixed discrete-continuous outcomes, and applies under a broad class of covariate-adaptive randomization schemes, including stratified block designs and simple random sampling. We derive the estimator's asymptotic distribution and show that it achieves the semiparametric efficiency bound. Simulation results demonstrate favorable finite-sample performance, and we demonstrate the method's practical relevance in an application to the Oregon Health Insurance Experiment. |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2509.15594 |
| By: | Nicolas Debarsy (Université de Lille) |
| Date: | 2025–09–10 |
| URL: | https://d.repec.org/n?u=RePEc:boc:bsug25:02 |
| By: | Vogl, Jonathan; Kleinebrahm, Max; Raab, Moritz; McKenna, Russell; Fichtner, Wolf |
| Abstract: | Electrified heating and mobility, the uptake of air conditioning and distributed energy resources are reshaping residential electricity demand and will require substantial investment. Yet the dependencies that drive present and future residential demand across sociodemographic characteristics, occupant activities, energy service demands, local technologies, and interactions with the overarching energy system remain poorly understood. Activity-based, bottom-up models make these dependencies explicit, better informing flexible operation and investment in low-carbon technologies. We review 45 activity-based residential models and assess coverage of appliances, domestic hot water, space heating and cooling, and mobility (electric vehicle charging), which are rarely considered jointly in one integrated model. We identify methodological gaps for consistently modeling behavior: To our knowledge, this is the first review to include activity-based mobility modeling, thereby identifying methodological gaps in consistent behavior modeling across residential energy services: First, most studies simulate single occupants in isolation rather than entire households, thereby overlooking interdependencies among occupants. Second, predominant use of Markov models or independent univariate sampling limits temporal consistency. Based on these findings, future studies should combine complementary behavioral datasets with sophisticated models (e.g., deep neural networks) capable of capturing complex dependencies to generate high-quality synthetic behavioral data as a basis for future bottom-up residential energy demand modeling. Further progress requires open datasets and reproducible validation frameworks to benchmark and compare activity-based models and to ensure consistent progress in the field. Currently, there is no model available in the literature that derives energy demand for thermal comfort, hot water, mobility, and other services consistently from one fundamental representation of household behavior. |
| Keywords: | household energy demand, activity schedules, occupancy behavior, activity modeling, sector coupling, mobility behavior, bottom-up demand modeling |
| Date: | 2025 |
| URL: | https://d.repec.org/n?u=RePEc:zbw:kitiip:328261 |
| By: | Salvatore Barbaro (Johannes-Gutenberg University, Germany); Anna-Sophie Kurella (Leibniz University, Hannover, Germany) |
| Abstract: | Dichotomous preferences are a widely assumed feature in social choice theory. Despite their prominence in theoretical models, the empirical validity of this assumption has remained largely unexplored. Nor is it always clear how dichotomous preferences are defined across different research contexts. This paper introduces two new concepts that weaken the strict dichotomy assumption and can each be tested empirically. Using CSES data and three experimental datasets—two from French presidential elections and one from a regional election in Austria—we examine how frequently the different forms of dichotomous preferences occur. In addition, the paper provides evidence on the relationship between ranking and approval ballots. The results suggest that while dichotomous preferences do not offer a perfect representation of voter preferences, they constitute an acceptable approximation, particularly among voters who approve more than two alternatives and among respondents with higher educational attainment levels. |
| Keywords: | Preferences, Dichotomous Preferences, Inequality Measures, Cluster Analysis |
| JEL: | D71 |
| Date: | 2025–10–02 |
| URL: | https://d.repec.org/n?u=RePEc:jgu:wpaper:2506 |
| By: | Vladim\'ir Hol\'y |
| Abstract: | We address the challenges of modeling high-frequency integer price changes in financial markets using continuous distributions, particularly the Student's t-distribution. We demonstrate that traditional GARCH models, which rely on continuous distributions, are ill-suited for high-frequency data due to the discreteness of price changes. We propose a modification to the maximum likelihood estimation procedure that accounts for the discrete nature of observations while still using continuous distributions. Our approach involves modeling the log-likelihood in terms of intervals corresponding to the rounding of continuous price changes to the nearest integer. The findings highlight the importance of adjusting for discreteness in volatility analysis and provide a framework for incroporating any continuous distribution for modeling high-frequency prices. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.09785 |
| By: | Flörchinger, Daniela; Perino, Grischa; Frondel, Manuel; Jarke, Johannes Stephan |
| Abstract: | Decommissioning of coal-fired power plants is a widely known emission abatement option, but one with a limited effect due to the EU Emissions Trading System (ETS). In contrast, tightening the cap in the EU ETS is a highly effective, but less known mitigation option. This article empirically analyzes whether informing individuals about the effectiveness of these abatement options increases support for more effective climate policies. The analysis is based on an online survey experiment involving actual cancellation of emission allowances and curbing the output of a coal-fired power plant. We find that preferences over abatement options are driven by their perceived effectiveness. Moreover, we provide causal evidence that voters update their preference rankings when exposed to relevant information. |
| Abstract: | Die Stilllegung von Kohlekraftwerken ist eine weithin bekannte Option zur Emissionsminderung, deren Wirkung jedoch aufgrund des EU-Emissionshandelssystems (EU-EHS) begrenzt ist. Im Gegensatz dazu ist die Verschärfung der Obergrenze im EU-EHS eine hochwirksame, aber weniger bekannte Minderungsoption. In diesem Artikel wird empirisch analysiert, ob die Aufklärung der Bevölkerung über die Wirksamkeit dieser Minderungsoptionen die Unterstützung für wirksamere Klimaschutzmaßnahmen erhöht. Die Analyse basiert auf einem Online-Umfrageexperiment, bei dem Emissionszertifikate tatsächlich gestrichen und die Leistung eines Kohlekraftwerks gedrosselt wurden. Wir stellen fest, dass die Präferenzen hinsichtlich der Emissionsminderungsmaßnahmen von ihrer wahrgenommenen Wirksamkeit abhängen. Darüber hinaus liefern wir kausale Belege dafür, dass Wähler ihre Präferenzrangfolge aktualisieren, wenn sie relevante Informationen erhalten. |
| Keywords: | coal phase-out, information provision, motivated reasoning, policy mix |
| JEL: | C93 D02 D83 D91 Q54 Q58 |
| Date: | 2025 |
| URL: | https://d.repec.org/n?u=RePEc:zbw:rwirep:328240 |
| By: | George Gui; Seungwoo Kim |
| Abstract: | Pre-experiment stratification, or blocking, is a well-established technique for designing more efficient experiments and increasing the precision of the experimental estimates. However, when researchers have access to many covariates at the experiment design stage, they often face challenges in effectively selecting or weighting covariates when creating their strata. This paper proposes a Generative Stratification procedure that leverages Large Language Models (LLMs) to synthesize high-dimensional covariate data to improve experimental design. We demonstrate the value of this approach by applying it to a set of experiments and find that our method would have reduced the variance of the treatment effect estimate by 10%-50% compared to simple randomization in our empirical applications. When combined with other standard stratification methods, it can be used to further improve the efficiency. Our results demonstrate that LLM-based simulation is a practical and easy-to-implement way to improve experimental design in covariate-rich settings. |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2509.25709 |
| By: | JINHO CHA (Gwinnett Technical College) |
| Abstract: | The growing prevalence of drift and shocks in modern decision environments exposes a gap between classical optimization theory and real-world practice. Standard models assume fixed objectives, yet organizations from hospitals to power grids routinely adapt to shifting priorities, noisy data, and abrupt disruptions. To address this gap, this study develops a dynamic inverse optimization framework that recovers hidden, time-varying preferences from observed allocation trajectories. The framework unifies identifiability analysis with regret guarantees conditions are established for existence and uniqueness of recovered parameters, and sharp static and dynamic regret bounds are derived to characterize responsiveness to gradual drift and sudden shocks. Methodologically, a drift-aware estimator grounded in convex analysis and online learning theory is introduced, with finite-sample guarantees on recovery accuracy. Computational experiments in healthcare, energy, logistics, and finance reveal heterogeneous recovery patterns, ranging from rapid resilience to persistent vulnerability. Overall, dynamic inverse optimization emerges as both a theoretical contribution and a broadly applicable diagnostic tool for benchmarking resilience, uncovering hidden behavioral shifts, and guiding policy interventions in complex stochastic systems. |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2509.14080 |