Prediction markets suffer from reduced liquidity and price accuracy for long-horizon events due to the opportunity cost of committed capital. Recently, major platforms have introduced interest-bearing positions to mitigate this "long-horizon problem." I evaluate this policy using agent-based simulations with large language model (LLM) traders in a 2 x 2 factorial design, varying time horizon (4 days vs. 2 years) and the presence of interest. While long horizons degrade accuracy, the observed pricing bias (0.72 percentage points) is significantly smaller than theoretical and prior empirical estimates. Paying interest eliminates approximately 83% of the horizon effect on accuracy and more than triples market participation (from 17% to 62% of wealth). These findings suggest the long-horizon problem may be overstated in existing literature and that interest-bearing positions are a highly effective intervention, primarily by incentivizing participation rather than correcting bias.

Large language models (LLMs) are increasingly used to provide health advice, yet evidence on how their accuracy varies across languages, topics and information sources remains limited. We assess how linguistic and contextual factors affect the accuracy of AI-based health-claim verification. We evaluated seven widely used LLMs on two datasets: (i) 1,975 legally authorised nutrition and health claims from UK and EU regulatory registers translated into 21 languages; and (ii) 9,088 journalist-vetted public-health claims from the PUBHEALTH corpus spanning COVID-19, abortion, politics and general health, drawn from government advisories, scientific abstracts and media sources. Models classified each claim as supported or unsupported using majority voting across repeated runs. Accuracy was analysed by language, topic, source and model. Accuracy on authorised claims was highest in English and closely related European languages and declined in several widely spoken non-European languages, decreasing with syntactic distance from English. On real-world public-health claims, accuracy was substantially lower and varied systematically by topic and source. Models performed best on COVID-19 and government-attributed claims and worst on general health and scientific abstracts. High performance on English, canonical health claims masks substantial context-dependent gaps. Differences in training data exposure, editorial framing and topic-specific tuning likely contribute to these disparities, which are comparable in magnitude to cross-language differences. LLM accuracy in health-claim verification depends strongly on language, topic and information source. English-language performance does not reliably generalise across contexts, underscoring the need for multilingual, domain-specific evaluation before deployment in public-health communication.

As economics scales, a key bottleneck is representing what papers claim in a comparable, aggregable form. We introduce evidence-annotated claim graphs that map each paper into a directed network of standardized economic concepts (nodes) and stated relationships (edges), with each edge labeled by evidentiary basis, including whether it is supported by causal inference designs or by non-causal evidence. Using a structured multi-stage AI workflow, we construct claim graphs for 44,852 economics papers from 1980-2023. The share of causal edges rises from 7.7% in 1990 to 31.7% in 2020. Measures of causal narrative structure and causal novelty are positively associated with top-five publication and long-run citations, whereas non-causal counterparts are weakly related or negative.

A popular approach to perform inference on a target parameter in the presence of nuisance parameters is to construct estimating equations that are orthogonal to the nuisance parameters, in the sense that their expected first derivative is zero. Such first-order orthogonalization allows the estimator of the nuisance parameters to converge at a slower-than-parametric rate. It may, however, not suffice when the nuisance parameters are very imprecisely estimated. Leading examples are models for panel and network data that feature fixed effects. In this paper, we show how, in the conditional-likelihood setting, estimating equations can be constructed that are orthogonal to any chosen order $q$, in that their leading $q$ expected derivatives are zero. This yields estimators of target parameters that are unaffected by the presence of nuisance parameters to order $q$. In an empirical illustration, we apply our method to a fixed-effect model of team production.

This paper studies multi-horizon Granger causality using high-dimensional local projections in sparse Vector Autoregressive (VAR) systems. Since local projection coefficients are nonlinear transformations of the underlying VAR parameters, existing approaches, such as de-biased least absolute shrinkage and selection operator (LASSO) and post-double-selection methods applied directly to local projections, lack a general justification, as sparsity of the VAR does not always propagate to higher horizons. We propose a two-step framework that avoids imposing sparsity at each horizon and delivers valid inference without relying on heteroskedasticityand autocorrelation-consistent (HAC) corrections. We establish large sample theory for the proposed estimators and develop feasible Wald tests. Monte Carlo experiments demonstrate improved size control across horizons relative to existing methods. An application to large financial systems illustrates horizon-specific connectedness.

We study the diffusion of a true and a false message (misinformation) when agents are biased and able to verify messages. As a recipient of a false message who verifies it becomes informed of the truth, a higher prevalence of misinformation can increase the prevalence of the truth. We uncover conditions such that this happens and discuss policy implications. Specifically, a planner aiming to maximize the prevalence of the truth should allow misinformation to circulate if: non-verified messages may be ignored, transmission of information is relatively low, and the planner's budget to induce verification is neither too low nor too high. Homophily increases the spread of misinformation, but also facilitates diffusion of truth, and leads to similar results on the effect of verification.

We explore stability and fairness considerations in decentralized networked markets with bilateral contracts, building on the trading networks framework [Hatfield et al., 2013]. In our trading network game, we show that a well-defined subset of Nash equilibria can be supported as competitive equilibria. Considering an offer-based trading dynamic as well as a stochastic price clock market, we prove new convergence results to Nash equilibrium and competitive equilibrium, providing a rationale for stability properties in decentralized, dynamic trading networks. Turning to the tension between fairness and (core) stability, we prove several negative results: inessential agents always receive zero utility in any core outcome, and even essential agents can get zero utility in all core outcomes.

This paper develops a unified framework that links firm-level predictive signals, cross-asset spillovers, and the stochastic discount factor (SDF). Signals and spillovers are jointly estimated by maximizing the Sharpe ratio, yielding an interpretable SDF that both ranks characteristic relevance and uncovers the direction of predictive influence across assets. Out-of-sample, the SDF consistently outperforms self-predictive and expected-return benchmarks across investment universes and market states. The inferred information network highlights large, low-turnover firms as net transmitters. The framework offers a clear, economically grounded view of the informational architecture underlying cross-sectional return dynamics.

We develop an empirical Bayes framework for experimental design that leverages information from prior related studies. When a researcher has access to estimates from previous studies on similar parameters, they can use empirical Bayes to estimate an informative prior over the parameter of interest in the new study. We show how this prior can be incorporated into a decision-theoretic experimental design framework to choose optimal design. The approach is illustrated via propensity score designs in stratified randomized experiments. Our theoretical results show that the empirical Bayes design achieves oracle-optimal performance as the number of prior studies grows, and characterize the rate at which regret vanishes. To illustrate the approach, we present two empirical applications--oncology drug trials and the Tennessee Project STAR experiment. Our framework connects the Bayesian meta-analysis literature to experimental design and provides practical guidance for researchers seeking to design more efficient experiments.

The long-standing unitary-actor assumption in strategy research -- treating firms as monolithic entities with coherent preferences -- misses that organizations are coalitions of individuals with diverse and often conflicting goals. Although behavioral perspectives have challenged this assumption, the field lacks an operational method for deriving an organizational utility function from the disparate preferences of its members and the specific structures used to aggregate them. We develop a mathematical framework that (i) maps individual utility functions into choice probabilities via a random-utility model, (ii) combines those probabilities using an explicit aggregation structure (e.g., unanimity or polyarchy), and (iii) recovers an organizational utility function that rationalizes the collective behavior. This establishes organizational utility functions as operationally meaningful: they summarize and predict organizational choice, yet are generally not simple averages of members' utilities. Instead, aggregation structures systematically reshape preferences -- unanimity approximates the pointwise minima of underlying utility functions, amplifying risk aversion; polyarchy approximates the pointwise maxima, promoting risk-seeking. We illustrate strategic implications in Cournot competition and principal-agent settings, showing how internal aggregation structures shift competitive and collaborative outcomes. Overall, the framework provides a parsimonious way to retrofit unitary-actor models with behaviorally grounded organizational preferences, reconciling the coalition view of the firm with rigorous and tractable strategic analysis.

The Vickrey-Clarke-Groves (VCG) mechanism is infamously revenue non-monotone in combinatorial auctions. I.e., when a buyer increases their value for a bundle of items, the total auction revenue may decrease. Combinatorial auctions exhibit complementarities which broadly result in complexities in auction theory. This brief note shows that non-monotonicity in multi-item auctions is not a result of complementarities, and in fact, VCG is revenue non-monotone even in matching markets.

I prove that competitive market outcomes require computational intractability. If P = NP, firms can efficiently solve the collusion detection problem, identifying deviations from cooperative agreements in complex, noisy markets and thereby making collusion sustainable as an equilibrium. If P != NP, the collusion detection problem is computationally infeasible for markets satisfying a natural instance-hardness condition on their demand structure, rendering punishment threats non-credible and collusion unstable. Combined with Maymin (2011), who proved that market efficiency requires P = NP, this yields a fundamental impossibility: markets can be informationally efficient or competitive, but not both. Artificial intelligence, by expanding firms' computational capabilities, is pushing markets from the competitive regime toward the collusive regime, explaining the empirical emergence of algorithmic collusion without explicit coordination.

Heterogeneous treatment effects (HTEs) are increasingly estimated using machine learning models that produce highly personalized predictions of treatment effects. In practice, however, predicted treatment effects are rarely interpreted, reported, or audited at the individual level but, instead, are often aggregated to broader subgroups, such as demographic segments, risk strata, or markets. We show that such aggregation can induce systematic bias of the group-level causal effect: even when models for predicting the individual-level conditional average treatment effect (CATE) are correctly specified and trained on data from randomized experiments, aggregating the predicted CATEs up to the group level does not, in general, recover the corresponding group average treatment effect (GATE). We develop a unified statistical framework to detect and mitigate this form of group bias in randomized experiments. We first define group bias as the discrepancy between the model-implied and experimentally identified GATEs, derive an asymptotically normal estimator, and then provide a simple-to-implement statistical test. For mitigation, we propose a shrinkage-based bias-correction, and show that the theoretically optimal and empirically feasible solutions have closed-form expressions. The framework is fully general, imposes minimal assumptions, and only requires computing sample moments. We analyze the economic implications of mitigating detected group bias for profit-maximizing personalized targeting, thereby characterizing when bias correction alters targeting decisions and profits, and the trade-offs involved. Applications to large-scale experimental data at major digital platforms validate our theoretical results and demonstrate empirical performance.

Demographics in Malaysia and Viet Nam are evolving rapidly, potentially disrupting traditional family support to older people. We estimate a set of Poisson random effects models with panel data from the Malaysia Ageing and Retirement Survey and the Viet Nam Aging Survey to analyze how living arrangements, marital status, and support from children influence the mental and physical health of older people. In Malaysia, having living children plays an important protective role for both mental and physical health, while living with a son appears to have a protective effect for physical health. Results are similar for Viet Nam, except older women, who are at greater risk of mental and physical health problems, appear to enjoy a greater protective effect for their mental health from a child living nearby than do men. Our analysis underscores the importance of social safety nets for the health of senior citizens living alone.

Background. Low earnings are associated with household insecurity. Direct Support Professionals (DSPs) provide support for people with intellectual and developmental disabilities, typically for wages close to state minimums, and may experience insecurity. Objective. The purpose of the study was to evaluate the prevalence of food and housing insecurity among DSPs. Methods. We conducted a statewide, cross-sectional survey of DSPs in New York State (2022-2023). Measures included detailed questions about food and housing insecurity. We used chi-square analyses and logistic regressions to examine relationships between insecurity and demographic characteristics as proxies for social determinants of health. A total of 4,503 DSPs responded to the survey. The analytic sample contained 2,766 respondents with complete data for all relevant variables. Results. Overall, 62.6% experienced food and/or housing insecurity, with over half of those respondents experiencing both. Insecurity was highest among DSPs with a disability (76.2%), DSPs of color (75.7%), and those with lower income (72.4%), but over 50% of DSPs across demographic groups experienced insecurity. Conclusions. The widespread insecurity this study demonstrates is an occupational hazard that reduces worker welfare. At the macro-level, household insecurity is a critical threat to the stability of the care and support delivery system. The human services sector is projected to grow rapidly in the future. If growth continues along low wage lines, it implies an equally rapid expansion of worker insecurity. Government action to raise pay and interventions that enhance food and housing security are needed to support workers in the care delivery system for people with intellectual and developmental disabilities.

Purpose. This paper examines the extent to which job satisfaction, requests for accommodations, and the likelihood of a request being granted vary by disability status. We further analyze whether being granted workplace accommodations moderates the relationship between work satisfaction and disability. Methods. We use a novel survey of healthcare workers centered on disability status, perceptions of work experiences, and the provision of accommodations. The data are used in a descriptive analysis and multiple regressions to examine the moderating effect of accommodations on the relationship between disability and indicators related to job satisfaction. Results. Results show that people with disabilities have more negative perceptions of their work experiences than people without disabilities. Although people with disabilities are more likely to request accommodations than people without disabilities, they are equally likely to have their requests wholly or partly granted. Regression results indicate that the negative relationships between disability status and most measures of work experience are largely eliminated when accounting for the disposition of accommodation requests. The main exception is turnover intentions, in which the adverse relationship with having a disability does not change even when an accommodation is granted. Partly granting accommodations is helpful only for some metrics of job experience. Conclusion. Our paper shows that fully granting accommodations can go a long way to closing the disability gap in job satisfaction between people with and without disabilities.

We propose a framework for testing the homogeneity of conditional average treatment effects (CATEs) across multiple experimental and observational studies. Our approach leverages multiple randomized trials to assess whether treatment effects vary with unobserved heterogeneity that differs across trials: if CATEs are homogeneous, this indicates the absence of interactions between treatment and unobservables in the mean effect. Comparing CATEs between experimental and observational data further allows evaluation of potential confounding: if the estimands coincide, there is no unobserved confounding; if they differ, deviations may arise from unobserved confounding, effect heterogeneity, or both. We extend the framework to settings with alternative identification strategies, namely instrumental variable settings and panel data with parallel trends assumptions based on differences in differences, where effects are identified only locally for subpopulations such as compliers or treated units. In these contexts, testing homogeneity is useful for assessing whether local effects can be extrapolated to the total population. We suggest a test based on double machine learning that accommodates high-dimensional covariates in a data-driven way and investigate its finite-sample performance through a simulation study. Finally, we apply the test to the International Stroke Trial (IST), a large multi-country randomized controlled trial in patients with acute ischaemic stroke that evaluated whether early treatment with aspirin altered subsequent clinical outcomes. Our methodology provides a flexible tool for both validating identification assumptions and understanding the generalizability of estimated treatment effects.

This paper examines bid requirements, where the government may cancel a procurement contract unless two or more bids are received. Using a first-price auction model with endogenous entry, we compare the bid requirement and reserve price mechanisms in terms of auction failure and procurement costs. We find that, in comparison with bid requirements, reserve prices can reduce procurement costs and substantially lower failure probabilities, especially when entry costs are high or signals are sufficiently informative. Bid requirements are more likely to result in zero entry, while reserve prices can sustain positive entry under broader conditions.

This paper studies the implementation of Bayes correlated equilibria in symmetric Bayesian games with nonatomic players, using direct information structures and obedient strategies. The main results demonstrate full implementation in a class of games with negative payoff externalities, such as congestion and Cournot games. Specifically, if the game admits a strictly concave potential in every state, then for every Bayes correlated equilibrium outcome with finite support and rational action distributions, there exists a direct information structure that implements this outcome under all equilibria. When the potential is weakly concave, we show that all equilibria implement the same expected total payoff. Additionally, all Bayes correlated equilibria, including those with infinite support or irrational action distributions, are approximately implemented.

We study policy counterfactuals that impose path restrictions on a policy instrument over a finite window. Under a sequential intervention design, we define two counterfactual objects, policy-peg impulse responses and policy-path effects, and we provide a novel local projection identification method. Under policy invariance and a linear moving average envelope, the local projection estimands coincide with the counterfactual outcomes implied by empirical vector autoregressions and linearized forward looking structural models, and the counterfactual outcomes are fully characterized by the relevant impulse responses. We also provide local projection identification of both counterfactual objects under an one-shot intervention design. In the empirical applications, we quantify the propagation of an oil-supply news shock under interest-rate pegs and study alternative liftoff paths during the post-pandemic tightening episode.

Control variables are routinely treated as exogenous, yet in many empirical settings they are themselves endogenous. This creates a dilemma: omitting controls may leave the treatment endogenous, while including them may contaminate identification. The problem is not resolved by instrumental variables when they are only conditionally valid. We show that average responses to the treatment remain identified under a rank condition called measurable separability, which accommodates endogenous controls. For parametric models, our approach amounts to estimating a nonparametric model that nests the parametric specification. For nonparametric models, our results imply that endogenous controls are generally innocuous under standard identification conditions, except in the presence of "bad controls". We further propose a test for endogenous controls. Simulation results and an empirical application demonstrate this prevalent issue and provide practical implications of our methods.

This paper proposes an information-based inference method for partially identified parameters in incomplete models that is valid both when the model is correctly specified and when it is misspecified. Key features of the method are: (i) it is based on minimizing a suitably defined Kullback-Leibler information criterion that accounts for incompleteness of the model and delivers a non-empty pseudo-true set; (ii) it is computationally tractable; (iii) its implementation is the same for both correctly and incorrectly specified models; (iv) it exploits all information provided by variation in discrete and continuous covariates; (v) it relies on Rao's score statistic, which is shown to be asymptotically pivotal.