The commonly used two-way fixed effects estimator is biased under correlated heterogeneity and can lead to misleading inference. The mean group estimator proposed by Pesaran and Smith (1995) is robust to correlated heterogeneity but requires the underlying individual estimates to have second-order moments that could fail if the number of estimated coefficients ($k$) is too close to the time dimension ($T$) of the panel. This paper focuses on panels where $k$ is close to $T$ (including $k=T$), and proposes a trimmed mean group (TMG) estimator that shrinks individual estimates most likely to fail the second-order moment condition. The TMG estimator is shown to be $n^{(1-α)/2}$-consistent and asymptotically normally distributed, where $α$ is determined by the degree to which individual estimates might not have moments. The $\sqrt{n}$ convergence rate is achieved only if all individual estimates have second-order moments. Extensions to panels with time effects are provided, and a new Hausman test of correlated heterogeneity is proposed. Small sample properties of the TMG estimator (with and without time effects) are investigated by Monte Carlo experiments and shown to be satisfactory. The proposed test of correlated heterogeneity is also shown to have the correct size and satisfactory power. The utility of the TMG approach is illustrated with an empirical application.

Industrial policy has returned to the centre of economic governance, particularly in the high-tech sectors where positive network externalities in demand make market dominance self-reinforcing. This paper studies the welfare effects of an industrial policy targeting a sector with network externalities in a two-country model with strategic trade and R&D investment. We show how the welfare consequences of this policy are determined by the interaction between the strength of the externality, the type of R&D, and the degree of product differentiation between the home and the imported goods. When externalities are weak or the goods are close substitutes, the business-stealing effect produces a race to the bottom that dissipates more surplus than it creates. Under sufficiently strong externalities and weak substitutability or complementarity of the goods, industrial policy competition can make both countries simultaneously better off compared to the laissez-faire outcome because of the mutual business-enhancement effect. The case is stronger for the product innovation than for the process innovation, as the former directly affects the demand and triggers a stronger network effects than the latter which operates indirectly through the supply. Thus, the network externalities create an opportunity for a win-win industrial policies, but its realisation depends on the market structure and the nature of innovation.

This paper studies proportional risk sharing at claim occurrence time in community-based insurance. Each participant is modeled by an individual Cramér-Lundberg surplus process, and, whenever a claim is reported within the pool, its cost is redistributed according to a fixed allocation matrix. We compare the infinite-time ruin probability of each participant under stand-alone operation and under pool participation. Our main result shows that pooling reduces, for every participant, the infinite-time ruin probability when claim severities belong to a common scale family, the allocation rule satisfies full allocation and actuarial fairness, and each transfer remains bounded by an individual capacity condition. The proof relies on a convex-order comparison between the losses borne inside the pool and the corresponding stand-alone losses. We also clarify the role of these assumptions by showing that, outside this framework, pooling need not be beneficial for all participants. Numerical illustrations with Exponential and LogNormal severities support the theoretical findings and highlight how the design of proportional sharing rules affects solvency. The paper thus provides simple and interpretable sufficient conditions under which transparent linear risk-sharing arrangements improve individual solvency in community-based insurance.

Time-of-use pricing is promoted to manage demand at public EV charging stations, yet its effectiveness depends on short run flexibility and local constraints. Using station by day by hour data from Shenzhen and Amsterdam, we estimate intraday price responsiveness on two margins, whether charging occurs in a station hour and, conditional on charging, delivered energy and occupancy time. High dimensional fixed effects absorb station by day demand shocks and hour of week patterns, so identification relies on within station, within day price variation under scheduled tariffs. Responses differ across cities. Shenzhen adjusts mainly through conditional intensity, whereas Amsterdam adjusts mainly through participation. Weather shifts responsiveness in opposite directions, with heat weakening responses in Shenzhen and rainfall strengthening participation responses in Amsterdam. Power upgrades typically outperform network densification except in transit-oriented areas.

The standard wage Phillips curve aggregates away from which workers reset wages when. I show this aggregation omits a first-order term: the covariance between workers' cost-push exposure and their reset frequency. I introduce two sufficient statistics and embed them in a multi-country HANK model calibrated to six euro-area economies. The omitted term generates 7 percent more cumulative core inflation in the baseline and 10--26 percent more when monetary policy is delayed. Two economies with identical openness can differ by 6.6 percentage-point-quarters solely from within-country composition. Targeted essentials subsidies reduce welfare loss by 32 percent relative to aggressive tightening. Out of sample, the model correctly predicts the persistence ranking across the UK, the US, and Japan.

This paper develops a unified framework for evaluating the optimal degree of task automation. Moving beyond binary automate-or-not assessments, we model automation intensity as a continuous choice in which firms minimize costs by selecting an AI accuracy level, from no automation through partial human-AI collaboration to full automation. On the supply side, we estimate an AI production function via scaling-law experiments linking performance to data, compute, and model size. Because AI systems exhibit predictable but diminishing returns to these inputs, the cost of higher accuracy is convex: good performance may be inexpensive, but near-perfect accuracy is disproportionately costly. Full automation is therefore often not cost-minimizing; partial automation, where firms retain human workers for residual tasks, frequently emerges as the equilibrium. On the demand side, we introduce an entropy-based measure of task complexity that maps model accuracy into a labor substitution ratio, quantifying human labor displacement at each accuracy level. We calibrate the framework with O*NET task data, a survey of 3,778 domain experts, and GPT-4o-derived task decompositions, implementing it in computer vision. Task complexity shapes substitution: low-complexity tasks see high substitution, while high-complexity tasks favor limited partial automation. Scale of deployment is a key determinant: AI-as-a-Service and AI agents spread fixed costs across users, sharply expanding economically viable tasks. At the firm level, cost-effective automation captures approximately 11% of computer-vision-exposed labor compensation; under economy-wide deployment, this share rises sharply. Since other AI systems exhibit similar scaling-law economics, our mechanisms extend beyond computer vision, reinforcing that partial automation is often the economically rational long-run outcome, not merely a transitional phase.

Business cycle synchronization between EU and Western Balkan candidate economies is usually modeled with aggregate time-domain correlations that mix short-run and long-run dynamics. This paper addresses that limitation by combining wavelet-based time-frequency decomposition with Bayesian zero-inflated beta regression. Using annual dyad-year data for 2001--2021, we estimate synchronization separately at shorter (1.5--4.5 years) and longer (4.5--8.5 years) horizons and relate each horizon to its correlates. The results show that EU--WB dyads are less synchronized than EU--EU dyads in the short run, and that trade deepening over time is more positively associated with short-run synchronization in EU--WB pairs. At longer horizons, the positive association between shared EU/EMU membership and synchronization weakens or reverses when the same country pair moves into deeper institutional integration, while differences across country pairs in average EU/EMU status become negligible. Over the same horizon, trade deepening within a pair is more consistently associated with synchronization, and more persistent structural dissimilarity is associated with lower synchronization. EU--WB dyads are no longer clearly less synchronized at these frequencies, and the remaining convergence pattern is more consistent with sectoral differences narrowing over time than with trade. These findings indicate that synchronization channels are horizon-dependent and that conclusions based on single-horizon correlation measures can obscure the distinction between short-term coupling and structural convergence.

Surveillance of diseases in a pandemic is an important part of public health policy. Diagnostic testing at the individual level is often infeasible due to resource constraints. To circumvent these constraints, group testing can be applied. The economic cost evaluation from the payer's perspective typically focuses only on deterministic costs which overlooks the substantial economic impact of productivity losses resulting from quarantine and workplace disruptions. The objective of this article is to develop a mathematical model for a retrospective economic evaluation of group testing that incorporates both deterministic costs and income-based economic loss. Group testing algorithms are revisited and simulated at optimized pool sizes to determine the required number of tests. Income data from the German Socio-Economic Panel are integrated into a mathematical model to capture the economic loss. Afterward, hybrid Monte Carlo experiments are conducted by evaluating the economic cost in the Coronavirus disease 2019 pandemic in Germany. Monte Carlo experiments show that the optimal choice of group testing algorithms changes substantially when income-based economic losses are included. Evaluations considering only deterministic costs systematically underestimate the total economic cost. Algorithms with a longer quarantine duration are less attractive than shorter quarantine duration if income-based economic loss is accounted for. The findings show that current evaluations underestimate the true economic cost. Group testing algorithms with shorter duration and fewer stages are preferred, even when they require a larger number of tests. These results underscore the importance of incorporating income-based economic loss into a mathematical model.

This paper derives closed-form unbiased estimators of central moments in multilevel random-effects models with unbalanced group sizes. In a two-level model, we provide unbiased estimators for the second, third, and fourth central moments under both group-level and observation-level averaging. In a three-level model, we provide unbiased estimators for the second and third central moments.

As variable renewable energy increases and more demand is electrified, we expect price formation in wholesale electricity markets to transition from being dominated by fossil fuel generators to being dominated by the opportunity costs of storage and demand management. In order to analyse this transition, we introduce a new method to investigate price formation based on a mapping from the dual variables of the energy system optimisation problem to the bids and asks of electricity suppliers and consumers. This allows us to build the full supply and demand curves in each hour. We use this method to analyse price formation in a sector-coupled, climate-neutral energy system model for Germany, PyPSA-DE, with high temporal resolution and myopic foresight in 5-year steps from 2020 until full decarbonisation in 2045. We find a clear transition from distinct price levels, corresponding to fossil fuels, to a smoother price curve set by variable renewable energy sources, batteries and electrolysis. Despite higher price volatility, the fully decarbonised system clears with non-zero prices in 75% of all hours. Our results suggest that flexibility and cross-sectoral demand bidding play a vital role in stabilising electricity prices in a climate-neutral future. These findings are highly relevant for guiding investment decisions and informing policy, particularly in support of dynamic pricing, the expansion of energy storage across multiple timescales, and the coordinated development of renewable and flexibility technologies.

Constructing confidence intervals for the value of an (unknown) optimal treatment policy is a fundamental problem in causal inference. Insight into the optimal policy value can guide the development of reward-maximizing, individualized treatment regimes. However, because the functional that defines the optimal value is non-differentiable, standard semi-parametric approaches for performing inference fail to be directly applicable. Many existing works circumvent non-differentiability by making the unrealistic assumption of zero probability of treatment non-response, i.e. that every unit responds (either positively or negatively) to an assigned treatment. Further, works that don't circumvent this restriction rely on refitting nuisance models a number of times proportional to the sample size. In this paper, we construct and analyze a simple, softmax smoothing-based estimator for the value of an optimal treatment policy. Our estimator applies in both static and dynamic treatment regimes, only requires fitting a constant number of nuisance models, and is statistically efficient when there is zero probability of non-response to treatment. Also, while our estimator does not require making semi-parametric restrictions, it can exploit them when they exist. We further show how our softmax smoothing approach can be used to estimate general parameters that are specified as a maximum of scores involving nuisance components, and look at conditional Balke and Pearl bounds and $L^1$ calibration error as salient examples.

While financial misconduct in advisory services persists despite regulation, the demand-side of market discipline, specifically the timing of investor detection, remains a critical bottleneck. Using approximately 55,700 FINRA BrokerCheck records, we analyze the detection lag between misconduct inception and formal reporting. We document a conditional average lag of 28.5 months, with a fat-tail exceeding eight years. Overt unauthorized activity reduces the lag by 35.7%, whereas sophisticated fraud extends it by 58.6%. Using method of moments quantile regression, we reveal a strategic masking gradient: the impact of advisor experience more than doubles at the 90th percentile relative to the 10th. Product opacity acts as an expanding shield: insurance-linked disputes extend latency by by 61.9% at the 10th percentile and by 90.0% at the 90th percentile of the distribution. Finally, market volatility serves as an asymmetric catalyst for discovery: a doubling of the VIX reduces the lag by 21.1% for rapid-discovery cases, but only 7.9% for deeply concealed schemes. These strategically managed discovery delays allow bad types to persist across multiple market cycles.

Using theory and experiments, this paper shows that the difficulty of making tradeoffs offers a parsimonious explanation for a wide range of behavioral phenomena. We develop a model of imprecise comparisons applicable to multiattribute, lottery, and intertemporal choice, which formalizes the idea that comparisons are difficult when they involve pronounced tradeoffs. Our model rationalizes a range of documented regularities, such as context effects, preference reversals, apparent probability weighting and hyperbolic discounting, and generates novel implications for behavior. We assess the explanatory power of our model in a series of choice experiments. Our model explains a large share of the variation in choice inconsistency across problems, and we document that manipulating tradeoffs reverses classic behavioral regularities, in line with its predictions.