Causal inference methods (instrumental variables, difference-in-differences, regression discontinuity, etc.) are primary tools used across many social science milieus. One area where their application has lagged however, is in the study of productivity and efficiency. A main reason for this is that the nature of the stochastic frontier model does not immediately lend itself to a causal framework when interest hinges on an error component of the model. This paper reviews the nascent literature on attempts to merge the stochastic frontier literature with causal inference methods. We discuss modeling approaches and empirical issues that are likely to be relevant for applied researchers in this area. This review shows how this model can be easily put within the confines of causal analysis, reviews existing work that has already made inroads in this area, addresses challenges that have yet to be met and discusses core findings.

Bastos, Geloso, and Bologna Pavlik (2026) argue that the US embargo explains less than one tenth of the difference in per capita income between Cuba and a counterfactual scenario in which the country did not follow socialist economic policies. We show that their results are driven by the use of an elasticity of income to trade openness that is neither representative nor a reasonable upper bound of the values found in the literature and by their choice to attribute the effect of the interaction between the embargo and other determinants of growth solely to those other determinants. We show that, once these problems are corrected, the embargo can account for a substantial fraction, and in some cases all, of Cuba's post 1959 economic underperformance.

Electricity price forecasting supports decision-making in energy markets and asset operation. Probabilistic forecasts are increasingly adopted to explicitly quantify uncertainty, typically issued as quantile predictions or ensembles of the full predictive distribution. However, how improvements in statistical forecast quality translate into economic value remains unclear. Battery storage arbitrage in day-ahead markets is a popular application-based benchmark for this purpose. We analyze quantile-based trading strategies (QBTS) and identify two critical flaws: they do not incentivize honest probabilistic forecasting and they ignore the intertemporal dependence structure of electricity prices. We therefore frame battery optimization as a stochastic program based on fully probabilistic forecasts and examine decision quality measurement for risk-neutral and risk-averse settings under different uncertainty models. Our discussion touches both sides of the coin: How reliable is the economic evaluation of forecasting models though (simplified) application studies - and how do improvements in statistical forecast quality for stochastic programs relate to the decision-quality and economic performance? We provide theoretical justification and empirical evidence from a case study on the German electricity market. Our results highlight the pitfalls of ranking forecasting models through battery trading strategies. We conclude with implications for evaluation practice and directions for future research in application-based forecast assessment.

We study whether zero-sum decision rules, maximin and minimax, harm agents' interests in positive-sum strategic environments relative to Nash equilibrium behavior or, more generally, than best response behaviour. Contrary to an influential evolutionary view, we give illustrations where maximin serves an agent's interests better than Nash equilibrium behaviour. We also show that these illustration are not atypical or idiosyncratic because, in our main result, the class of such games where a maximin profile strictly Pareto dominates all Nash equilibria has the same cardinality as the class of games in which a Nash equilibrium strictly Pareto dominates all maximin profiles. Thus, neither behavior is generally superior. We further identify additional mechanisms favoring maximin over Nash equilibrium, including coordination failures under multiple equilibria, where maximin can outperform Nash play in realised-pay-off terms. A systematic analysis of strictly ordinal symmetric 3x3 games shows that these effects arise with non-trivial frequency. Our findings, therefore, suggest that the observed rise in zero-sum thinking in many rich countries, when associated with a maximin decision rule, will not be readily displaced through its generation of inferior pay-offs.

How should researchers conduct causal inference when the outcome of interest is latent and measured imperfectly by multiple indicators? We develop a general nonparametric framework for identifying and estimating average treatment effects on latent outcomes in randomized experiments. We show that latent-outcome estimation faces two distinct noncomparability challenges. First, across studies, different measurement systems may cause estimators to target different empirical quantities even when the underlying latent treatment effect is the same. Second, within a study, different indicators may have different and possibly nonlinear relationships with the same latent outcome, making them not directly comparable. To address these challenges, we propose a design-based approach built around nonparametric bridge functions. We show that these bridge functions can be characterized and identified. Estimation relies on a debiasing procedure that permits valid inference even when the bridge functions are weakly identified. Simulations demonstrate that standard methods, such as principal components analysis and inverse covariance weighting, can generate spurious cross-study differences, whereas our approach recovers comparable latent treatment effects. Overall, the framework provides both a general strategy for causal inference with latent outcomes and practical guidance for designing measurements that support identification, comparability, and efficient estimation.

We assess the advantage of combining univariate and multivariate portfolio risk forecasts with the aid of forecast reconciliation techniques. In our analyzes, we assume knowledge of portfolio weights, a standard for portfolio risk management applications. With an extensive simulation experiment, we show that, if the true covariance is known, forecast reconciliation improves over a standard multivariate approach, in particular when the adopted multivariate model is misspecified. However, if noisy proxies are used, correctly specified models and the misspecified ones (for instance, neglecting spillovers) turn out to be, in several cases, indistinguishable, with forecast reconciliation still providing improvements. The noise in the covariance proxy plays a crucial role in determining the improvement of both the forecast reconciliation and the correct model specification. An empirical analysis shows how forecast reconciliation can be adopted with real data to improve traditional GARCH-based portfolio variance forecasts.

We study a simple problem of allocating common-value goods. The designer seeks to allocate the goods to as many unit-demand agents as possible without monetary transfers, while agents, who possess partial private information about the goods, are willing to receive them only when the goods are of high value. Mechanisms screen each agent's private information using the information of other agents, and in doing so shape what agents learn from other agents about the value of the goods. The optimal mechanism can be summarized by two parameters: one adjusts the allocation probability, while the other governs the amount of learning induced by allocation. Although the designer prefers to allocate the goods, the optimal mechanism excludes some agents and, as a result, may withhold allocation even when all agents would be willing to receive them. The optimal mechanism has the same structure even when payments are available, but it may not exclude any agent and may involve strictly positive payments that are decreasing in allocation.

This paper introduces a new approach for bubble detection based on mixed causal and noncausal autoregressive processes and their tail process representation during an explosive episode. Departing from traditional definitions of bubbles as nonstationary and temporarily explosive processes, we adopt a perspective in which prices are assumed to follow a strictly stationary process, with the bubble considered an intrinsic component of its nonlinear dynamics. The proposed approach provides a bubble indicator for detecting bubbles and measuring their duration. We implement our strategy to investigate the phenomenon called the "green bubble" in the field of renewable energy investment.

Food market accessibility is a critical yet underexplored dimension of food systems, particularly in low- and middle-income countries. In this paper, we present a continent-wide assessment of spatial food market accessibility in Africa, integrating open geospatial data from OpenStreetMap and the World Food Programme. We compare three complementary metrics: travel time to the nearest market, market availability within a 30-minute threshold, and an entropy-based measure of spatial distribution, to quantify accessibility across diverse settings. Our analysis reveals pronounced disparities: rural and economically disadvantaged populations face substantially higher travel times, limited market reach, and less spatial redundancy. These accessibility patterns align with socioeconomic stratification, as measured by the Relative Wealth Index, and moderately correlate with food insecurity levels, assessed using the Integrated Food Security Phase Classification. We find pronounced disparities in accessibility: rural and economically disadvantaged populations face substantially longer travel times and reduced market availability, with some areas requiring several hours of travel. Overall, results suggest that access to food markets reflects broader geographic and economic inequalities and plays a relevant role in shaping food security outcomes. This framework provides a scalable, data-driven approach for identifying underserved regions and supporting equitable infrastructure planning and policy design across diverse African contexts.

In this paper, we consider estimating spot/instantaneous volatility matrices of high-frequency data collected for a large number of assets. We first combine classic nonparametric kernel-based smoothing with a generalised shrinkage technique in the matrix estimation for noise-free data under a uniform sparsity assumption, a natural extension of the approximate sparsity commonly used in the literature. The uniform consistency property is derived for the proposed spot volatility matrix estimator with convergence rates comparable to the optimal minimax one. For the high-frequency data contaminated by microstructure noise, we introduce a localised pre-averaging estimation method that reduces the effective magnitude of the noise. We then use the estimation tool developed in the noise-free scenario, and derive the uniform convergence rates for the developed spot volatility matrix estimator. We further combine the kernel smoothing with the shrinkage technique to estimate the time-varying volatility matrix of the high-dimensional noise vector. In addition, we consider large spot volatility matrix estimation in time-varying factor models with observable risk factors and derive the uniform convergence property. We provide numerical studies including simulation and empirical application to examine the performance of the proposed estimation methods in finite samples.

Altruism is fundamental to human societies, fostering cooperation and social cohesion. Recent studies suggest that large language models (LLMs) can display human-like prosocial behavior, but the internal computations that produce such behavior remain poorly understood. We investigate the mechanisms underlying LLM altruism using sparse autoencoders (SAEs). In a standard Dictator Game, minimal-pair prompts that differ only in social stance (generous versus selfish) induce large, economically meaningful shifts in allocations. Leveraging this contrast, we identify a set of SAE features (0.024% of all features across the model's layers) whose activations are strongly associated with the behavioral shift. To interpret these features, we use benchmark tasks motivated by dual-process theories to classify a subset as primarily heuristic (System 1) or primarily deliberative (System 2). Causal interventions validate their functional role: activation patching and continuous steering of this feature direction reliably shift allocation distributions, with System 2 features exerting a more proximal influence on the model's final output than System 1 features. The same steering direction generalizes across multiple social-preference games. Together, these results enhance our understanding of artificial cognition by translating altruistic behaviors into identifiable network states and provide a framework for aligning LLM behavior with human values, thereby informing more transparent and value-aligned deployment.

In the midst of the COVID-19 pandemic in 2020, the Australian Government launched two programs to incentivise new apprentices to start and complete apprenticeships -- the Boosting Apprenticeship Commencements (BAC) and Completing Apprenticeship Commencements (CAC) programs. These programs were wage subsidies to encourage employers to take on or retain apprentices. This paper evaluates the impact of these programs on apprenticeship commencements and completions taking a mixed-methods approach combining econometric modelling and interviews with stakeholders including employers and peak bodies. The programs led to a 70\% increase in commencement of apprenticeships but do not seem to have boosted retention rates. There appears to be a small increase in cancellation rates suggesting lower eventual completion rates compared to previous cohorts. Cancellation rates were higher for non-trade commencements (7\% increase) during BAC, but slightly lower for trade commencements (0.7\% decrease). We find this effect in non-trade apprenticeships was likely driven by `sharp practice' where some employers took advantage of the BAC by converting existing employees over to apprenticeships to attract the wage subsidy with no intention of having these employees stay as apprentices beyond the period of the BAC's generous subsidy. While the BAC / CAC were successful in many of their goals, there are several lessons that can be learnt from its design. In particular, the need to implement the program quickly meant early design choices inadvertently encouraged `sharp practice' and a rush for places that placed strain on the training sector. However, employers appreciated the front-loading of payments which provided the most financial support when apprentices were new and at their least productive.

In random assignment, fairness is often captured by stochastic-dominance envy-freeness (SD-EF). We observe that assignments satisfying SD-EF may admit decompositions that result in each agent envying another agent with high probability. To address this, we introduce decomposition envy-freeness (Dec-EF), which is a property of a decomposition rather than of an assignment matrix. We show that an SD-EF assignment matrix always admits a Dec-EF decomposition when there are at most three agents or the agents have at most two distinct preferences.

We study a new measure of codependency in the second moment of a continuous-time multivariate asset price process, which we name the realized copula of volatility. The statistic is based on local volatility estimates constructed from high-frequency asset returns and affords a nonparametric estimator of the empirical copula of the latent stochastic volatility. We show consistency of our estimator with in-fill asymptotic theory, either with a fixed or increasing time span. In the latter setting, we derive a functional central limit theorem for the empirical process associated with the measurement error of the time-invariant marginal copula of volatility. We also develop a goodness-of-fit test to evaluate hypotheses about the shape of the latter. In a simulation study, we demonstrate that our estimator is a good proxy of both the empirical and marginal copula of volatility, even with a moderate amount of high-frequency data recorded over a relatively short sample. The goodness-of-fit test is found to exhibit size control and excellent power. We implement our framework on high-frequency transaction data from futures contracts that track the U.S. equity and treasury bond market. A Gumbel copula is found to offer a near-perfect bind between the realized variance processes in these data.

We propose a new model specification test for multiple-equation systems with cross-equation error and dynamic regressor--error dependences. Conventional tests often rely on exogeneity conditions strong enough to ensure consistency of the OLS estimator. These exogeneity conditions are violated when regressors and errors are dynamically dependent, rendering conventional model specification tests invalid. To address these limitations, we clarify the relationship among alternative exogeneity conditions, characterize the consistency of competing multiple-equation estimators, and propose a generalized Durbin estimator for multiple-equation systems with an intercept, cross-equation error and regressor--error dependences. We show that our estimator remains consistent under the weakest exogeneity condition. We then derive its asymptotic distribution and construct Wald tests. Our Monte Carlo experiments confirm that the bootstrap-based Wald test substantially improves finite-sample size control. An application of the bootstrap-based Wald test to the Fama--French multifactor models leaves the null hypothesis unrejected in cases where competing FGLS-based tests reject it.

We study a sequential mechanism design problem in which a principal seeks to elicit truthful reports from multiple rational agents while starting with no prior knowledge of agents' beliefs. We introduce Distributionally Robust Adaptive Mechanism (DRAM), a general framework combining insights from both mechanism design and online learning to jointly address truthfulness and cost-optimality. Throughout the sequential game, the mechanism estimates agents' beliefs and iteratively updates a distributionally robust linear program with shrinking ambiguity sets to reduce payments while preserving truthfulness. Our mechanism guarantees truthful reporting with high probability while achieving $\tilde{O}(\sqrt{T})$ cumulative regret, and we establish a matching lower bound showing that no feasible adaptive mechanism can asymptotically do better. The framework generalizes to plug-in estimators, supporting structured priors and delayed feedback. To our knowledge, this is the first adaptive mechanism under general settings that maintains truthfulness and achieves optimal regret when incentive constraints are unknown and must be learned.

The FAO-GAEZ productivity data are widely used in Economics. However, the empirical literature rarely discusses measurement error. We use two proxies to derive analytical bounds around the effect of agricultural productivity in a setting with nonclassical measurement error. These bounds rely on assumptions weaker than those imposed in empirical studies and exhaust the information contained in the first two data moments. We reevaluate three influential studies, finding wide intervals around the effects of agricultural productivity. These results call for caution, highlighting the limits of our knowledge about these effects. Our methodology has broad applications in empirical research involving mismeasured variables.

Estimating the causal effects of interventions is crucial to policy and decision-making, yet outcome data are often missing or subject to non-standard measurement error. While ground-truth outcomes can sometimes be obtained through costly data annotation or follow-up, budget constraints typically allow only a fraction of the dataset to be labeled. We address this challenge by optimizing which data points should be sampled for outcome information in order to improve efficiency in average treatment effect estimation with missing outcomes. We derive a closed-form solution for the optimal batch sampling probability by minimizing the asymptotic variance of a doubly robust estimator for causal inference with missing outcomes. Motivated by our street outreach partners, we extend the framework to costly annotations of unstructured data, such as text or images in healthcare and social services. Across simulated and real-world datasets, including one of outreach interventions in homelessness services, our approach achieves substantially lower mean-squared error and recovers the AIPW estimate with fewer labels than existing baselines. In practice, we show that our method can match confidence intervals obtained with 361 random samples using only 90 optimized samples - saving 75% of the labeling budget.

Feedback from artificial intelligence (AI) is increasingly easy to access and research has already established that people learn from it. But individuals choose when and how to seek such feedback, and more engaged and motivated individuals may seek it more, creating an illusion of effectiveness that masks self-selection. We investigate how the endogenous choice to seek AI feedback shapes both individual learning and collective outcomes. Using data from over five years and 52,000 individuals on an online chess platform, we show that motivated and higher-skilled individuals self-select into AI feedback use-and use it more productively. This self-selection creates an illusion of AI effectiveness: apparent learning gains disappear once endogenous motivation is accounted for. This same selection mechanism drives two population-level consequences. Because motivated, higher-skilled individuals benefit disproportionately, AI access widens the skill gap. And because individuals exposed to centralized AI feedback converge on common input from a centralized AI source, intellectual diversity declines. Leveraging 42 platform-level natural experiments, we show this diversity reduction is causal. Self-selection into AI use thus connects individual-level learning dynamics to collective-level consequences-a micro-macro linkage with implications for organizational learning, human capital development, and the design of AI-augmented work.

Aesthetics drives product differentiation in industries such as fashion, interior decor, luxury goods, real estate and hospitality. However, visual differentiation is hard to encode in formal economic analysis. This paper analyses millions of purchase records from H\&M in the Netherlands, including product images, text descriptions, prices, and consumer demographics. I fine-tune Fashion CLIP embeddings with a three-tower approach that builds separate channels for product visuals and text, consumer history, and price, which makes downstream analysis tractable and scalable. The embeddings feed a latent-class deep demand system that captures price and taste sensitivities through deep nets, recovers rich substitution patterns, reveals meaningful heterogeneity, and performs much better than competing alternatives. Then, a supply-side inversion recovers sensible markups and costs and supports conduct tests and counterfactuals on sustainability practices. I also estimate machine learning hedonic pricing models that perform much better than competing alternatives. This model allows us to construct quality-adjusted price indices, make it possible to price completely new designs, and with an Oaxaca-Blinder decomposition reveal the underlying sources of price changes. Finally, a Poisson event study around the COVID-19 lockdown shows that the range of demand responses across embedding-based product and user clusters exceeds anything recoverable from simple text-based attributes or demographic labels alone. The methodology is portable to any market where products are differentiated along sensory dimensions that are hard to encode but meaningfully important for consumer choices.

Peer influence on effort devoted to some activity is often studied when effort is unobserved, and the researcher instead observes an outcome that combines effort with other shocks. For instance, in education, achievement measures such as GPA reflect both effort and idiosyncratic GPA shocks. We propose an alternative approach that circumvents this approximation. Our framework distinguishes unobserved shocks to GPA that do not affect effort from preference shocks that do affect effort levels. We show that peer effects estimates obtained using our approach can differ significantly from classical estimates (where effort is approximated) if the network includes isolated students. Applying our approach to data on high school students in the United States, we find that peer effect estimates relying on GPA as a proxy for effort are 40% lower than those obtained using our approach.