The celebrated Myerson--Satterthwaite theorem shows that in bilateral trade, no mechanism can be simultaneously fully efficient, Bayesian incentive compatible (BIC), and budget balanced (BB). This naturally raises the question of how closely the gains from trade (GFT) achievable by a BIC and BB mechanism can approximate the first-best (fully efficient) benchmark. The optimal BIC and BB mechanism is typically complex and highly distribution-dependent, making it difficult to characterize directly. Consequently, much of the literature analyzes simpler mechanisms such as the Random-Offerer (RO) mechanism and establishes constant-factor guarantees relative to the first-best GFT. An important open question concerns the worst-case performance of the RO mechanism relative to first-best (FB) efficiency. While it was originally hypothesized that the approximation ratio $\frac{\text{GFT}_{\text{FB}}}{\text{GFT}_{\text{RO}}}$ is bounded by $2$, recent work provided counterexamples to this conjecture: Cai et al. proved that the ratio can be strictly larger than $2$, and Babaioff et al. exhibited an explicit example with ratio approximately $2.02$. In this work, we employ AlphaEvolve, an AI-guided evolutionary search framework, to explore the space of value distributions. We identify a new worst-case instance that yields an improved lower bound of $\frac{\text{GFT}_{\text{FB}}}{\text{GFT}_{\text{RO}}} \ge \textbf{2.0749}$. This establishes a new lower bound on the worst-case performance of the Random-Offerer mechanism, demonstrating a wider efficiency gap than previously known.

This paper studies optimal consumption and saving decisions under uncertainty about the transition dynamics of the economic environment. We consider a general optimal savings problem in which the exogenous state governing discounting, capital returns, and nonfinancial income follows a Markov process with unknown transition probability, and agents update their beliefs over time through Bayesian learning. Despite the added endogenous state from belief updating, we establish the existence, uniqueness, and key structural properties of the optimal policy, including monotonicity and concavity. We also develop an efficient computational method and use it to study how transition uncertainty and learning interact with precautionary motives and wealth accumulation, highlighting a dynamic mechanism through which uncertainty about regime persistence shapes consumption dynamics and long-run household wealth.

Data in modern economic and financial applications often arrive as a stream, requiring models and inference to be updated in real time -- yet most semiparametric methods remain batch-based and computationally impractical in large-scale streaming settings. We develop an online learning framework for semiparametric monotone index models with an unknown monotone link function. Our approach uses a two-phase learning paradigm. In a warm-start phase, we introduce a new online algorithm for the finite-dimensional parameter that is globally stable, yielding consistent estimation from arbitrary initialization. In a subsequent rate-optimal phase, we update the finite-dimensional parameter using an orthogonalized score while learning the unknown link via an online sieve method; this phase achieves optimal convergence rates for both components. The procedure processes only the most recent data batch, making it suitable when data cannot be stored (e.g., memory, privacy, or security constraints), and its resulting parameter trajectories enable online inference such as confidence regions--on parameters including policy-effect analysis with negligible additional computation. Monte Carlo experiments on both simulated and real data show adequate performance especially relative to full sample methods.

Automated Market Makers (AMMs) are a central component of decentralized exchanges, yet their equilibrium foundations and microeconomic mechanisms remain incompletely understood. This paper develops a dynamic equilibrium framework for Constant Function Market Makers (CFMMs) that formalizes the strategic interaction between arbitrageurs and liquidity providers (LPs) over time. We make three main contributions. First, we derive and empirically validate an intrinsic buy-sell asymmetry in CFMM price impact. Even in the absence of directional price movements, the geometric structure of constant product AMMs implies systematically different execution costs for buying and selling, a prediction that we confirm using on-chain transaction data. Second, we characterize the optimization problems of arbitrageurs and LPs in closed form, incorporating slippage and fees. In a baseline environment with only informed arbitrageurs, we show that providing liquidity is strictly dominated for LPs: arbitrage-driven price corrections generate negative jump returns that cannot be offset by fees, yielding a degenerate equilibrium with minimal liquidity provision. Third, motivated by empirical evidence, we extend the model to include agent heterogeneity, endogenous gas fees, and time varying volatility. In this extended environment, noise trading, arbitrage races, and execution costs jointly determine LP returns, giving rise to an interior equilibrium in which optimal liquidity provision is non-monotonic in volatility and exhibits a hump-shaped relationship. Overall, this paper builds a dynamic equilibrium model calibrated on extensive data that characterize the complex interaction between informed arbitrageurs, noise traders, and liquidity providers.

We argue that negative skew and positive mean of the distribution of stock returns are largely due to the broken symmetry of stochastic volatility governing gains and losses. Starting with stochastic differential equations for stock returns and for stochastic volatility we argue that the distribution of stock returns can be effectively split in two -- for gains and losses -- assuming difference in parameters of their respective stochastic volatilities. A modified Jones-Faddy skew t-distribution utilized here allows to reflect this in a single organic distribution which tends to meaningfully capture this asymmetry. We illustrate its application on distribution of daily S&P500 returns, including analysis of its tails.

We develop estimation and inference methods for a stylized macroeconomic model with potentially multiple behavioural equilibria, where agents form expectations using a constant-gain learning rule. We first show geometric ergodicity of the underlying process to study in a second step (strong) consistency and asymptotic normality of the nonlinear least squares estimator for the structural parameters. We propose inference procedures for the structural parameters and uniform confidence bands for the equilibria. When equilibrium solutions are repeated, mixed convergence rates and non-standard limit distributions emerge. Monte Carlo simulations and an empirical application illustrate the finite-sample performance of our methods.

In settings where units' outcomes are affected by others' treatments, there has been a proliferation of ways to quantify effects of treatments on outcomes, including via indirect exposure to other units' treatments. Here we consider two properties we might want estimands to have: being interpretable as summaries of unit-level effects, and being relevant to choice of a policy governing treatment assignment. We characterize many estimands as involving one of two orders of averaging over units in a population and over treatment assignments under a policy. The more common representation often results in quantities that are insufficient for optimal policy choice. This occurs because these quantities summarize outcomes under homogeneous exposure to treatment, but even homogeneous policies often lead to heterogeneous exposures. The other representation often yields quantities that lack an interpretation as summaries of unit-level effects. We argue that, among various estimands, the expected average outcome, which averages over units and treatment assignments in either order, deserves further attention from researchers. This estimand, or contrasts among these estimands under different policies, is both a summary of unit-level effects and is sufficient for optimal policy choice with utilitarian welfare.

This paper presents GMM and M estimators and their asymptotic properties for network-dependent data. To this end, I build on Kojevnikov, Marmer, and Song (KMS, 2021) and develop a novel uniform law of large numbers (ULLN), which is essential to ensure desired asymptotic behaviors of nonlinear estimators (e.g., Newey and McFadden, 1994, Section 2). Using this ULLN, I establish the consistency and asymptotic normality of both GMM and M estimators. For practical convenience, complete estimation and inference procedures are also provided.

We develop a framework for the optimal pricing and product design of LLMs in which a provider sells menus of token budgets to users who differ in their valuations across a continuum of tasks. Under a homogeneous production technology, we show that users' high-dimensional type profiles are summarized by a scalar index, reducing the seller's problem to one-dimensional screening. The optimal mechanism takes the form of committed-spend contracts: buyers pay for a budget that they allocate across token classes priced at marginal cost. We extend the analysis to environments with multiple differentiated models and to competition between a proprietary leader and an open-source fringe, showing that competitive pressure reshapes both the intensive and extensive margins of compute provision. Each element of our theory (token-budget menus, maximum- and minimum-spend plans, multi-model versioning, and linear API pricing) has a direct counterpart in the observed pricing practices of providers such as Anthropic, OpenAI, and GitHub.

Algorithmic agents are used in a variety of competitive decision-making settings, including pricing contexts that range from online retail to residential home rental. We study the emergence of algorithmic collusion when competing agents employ multi-armed bandit algorithms and competition is modeled as a repeated Prisoner's Dilemma game. Notably, agents in our setting perform online learning with no prior model of game structure and have no direct knowledge of competitor states or actions, thus they cannot learn strategies that depend on these factors. These context-free bandits nonetheless frequently learn seemingly collusive behavior, a phenomenon we term naive collusion. Our results reveal that whether naive collusion emerges depends starkly on the choice of behavior policy employed by bandit learners. The mechanism underpinning the emergence of collusive outcomes is synchronicity in agent action plays, where synchronicity captures how often agents play the same action. We show that in the long-run, naive algorithmic collusion never emerges when both agents use a broad class of persistently random algorithms, including the epsilon-greedy algorithm without epsilon decay, sometimes emerges when both agents use greedy-in-the-limit algorithms which feature randomness during exploration but are asymptotically deterministic, and always emerges when both agents use deterministic bandit learning algorithms like those in the well-known upper confidence bound (UCB) family. We highlight market and algorithmic conditions under which one can and cannot predict a priori whether collusion will occur. Our findings have several policy implications: preventing pricing algorithms from conditioning their actions on competitor prices may not preclude algorithmic collusion, symmetry in algorithms may increase collusion potential, and the emergence of algorithmic collusion is path dependent.

This paper studies the identification of Structural Vector Autoregressions (SVARs) exploiting a break in the variances of the structural shocks. Point-identification for this class of models relies on an eigen-decomposition involving the covariance matrices of reduced-form errors and requires that all the eigenvalues are distinct. This point-identification, however, fails in the presence of multiplicity of eigenvalues. This occurs in an empirically relevant scenario where, for instance, only a subset of structural shocks had the break in their variances, or where a group of variables shows a variance shift of the same amount. Together with zero or sign restrictions on the structural parameters and impulse responses, we derive the identified sets for impulse responses and show how to compute them. We perform inference on the impulse response functions, building on the robust Bayesian approach developed for set identified SVARs. To illustrate our proposal, we present an empirical example based on the literature on the global crude oil market where the identification is expected to fail due to multiplicity of eigenvalues.

We develop a new identification strategy for average treatment effects on the treated (ATT) in panel data with discrete outcomes. Standard difference-in-differences (DiD) relies on parallel trends, which is frequently violated in categorical settings due to mean reversion, out-of-bounds counterfactuals, and ill-defined trends for multi-category outcomes. We propose an alternative identification strategy with transition independence: absent treatment, transition dynamics conditional on pre-treatment outcomes are identical between control and treated groups. To capture unobserved heterogeneity, we introduce a latent-type Markov structure delivering type-specific and aggregate treatment effects from short panels. Three empirical applications yield ATT estimates substantially different from conventional DiD.

We propose a simple binarization of predictors, an "at-risk" transformation, as an alternative to the standard practice of using continuous, standardized variables in recession forecasting models. By converting predictors into indicators of unusually weak states based on a thresholding rule estimated from training data, we demonstrate their ability to capture the discrete nature of rare events such as U.S. recessions. Using a large panel of monthly U.S. macroeconomic and financial data, we show that binarized predictors consistently improve out-of-sample forecasting performance, often making linear models competitive with flexible machine learning methods, and that the gains are particularly pronounced around the onset of recessions.

A standard assumption in the Bayesian estimation of linear regression models is that the regressors are exogenous in the sense that they are uncorrelated with the model error term. In practice, however, this assumption can be invalid. In this paper, using the exponentially tilted empirical likelihood framework, we develop a Bayes factor test for endogeneity that compares a base model that is correctly specified under exogeneity but misspecified under endogeneity against an extended model that is correctly specified in either case. We provide a comprehensive study of the log-marginal exponentially tilted empirical likelihood. We demonstrate that our testing procedure is consistent from a frequentist point of view: as the sample grows, it almost surely selects the base model if and only if the regressors are exogenous, and the extended model if and only if the regressors are endogenous. The methods are illustrated with simulated data, and problems concerning the causal effect of automobile prices on automobile demand and the causal effect of potentially endogenous airplane ticket prices on passenger volume.

This paper develops a unified identification framework for counterfactual analysis in incomplete models characterized by support and moment restrictions. I demonstrate that identifying structural parameters and conducting counterfactual analyses are isomorphic tasks. By embedding counterfactual restrictions within an augmented structural model specification, this approach bypasses the conventional "estimate-then-simulate" workflow and the need to simulate outcomes from models with set predictions. To make this approach operational, I extend sharp identification results for the support-function approach beyond the integrable boundedness condition that is imposed in sharp random-set characterizations but may be violated in economically relevant counterfactual analyses. Under minimal regularity conditions, I prove that the support-function approach remains sharp for the $moment$ $closure$ of the identified set. Furthermore, I introduce an irreducibility condition requiring all support implications to be made explicit. I show that for irreducible models, the identified set and its moment closure are statistically indistinguishable in finite samples. Together, these results justify using support-function methods in counterfactual settings where traditional sharpness fails and clarify the distinct roles of support and moment restrictions in empirical practice.

We introduce ForeComp, an R package for comparing predictive accuracy using Diebold-Mariano type tests of equal predictive ability with standard and fixed smoothing inference. The package provides a common interface for loss differential based testing and includes Plot Tradeoff, a visual diagnostic for bandwidth sensitivity and the size-power tradeoff. We illustrate the toolkit with Survey of Professional Forecasters applications and Monte Carlo evidence on finite-sample performance.

Large language models (LLMs) have enabled agent-based systems that aim to automate scientific research workflows. Most existing approaches focus on fully autonomous discovery, where AI systems generate research ideas, conduct analyses, and produce manuscripts with minimal human involvement. However, empirical research in economics and the social sciences poses additional constraints: research questions must be grounded in available datasets, identification strategies require careful design, and human judgment remains essential for evaluating economic significance. We introduce HLER (Human-in-the-Loop Economic Research), a multi-agent architecture that supports empirical research automation while preserving critical human oversight. The system orchestrates specialized agents for data auditing, data profiling, hypothesis generation, econometric analysis, manuscript drafting, and automated review. A key design principle is dataset-aware hypothesis generation, where candidate research questions are constrained by dataset structure, variable availability, and distributional diagnostics, reducing infeasible or hallucinated hypotheses. HLER further implements a two-loop architecture: a question quality loop that screens and selects feasible hypotheses, and a research revision loop where automated review triggers re-analysis and manuscript revision. Human decision gates are embedded at key stages, allowing researchers to guide the automated pipeline. Experiments on three empirical datasets show that dataset-aware hypothesis generation produces feasible research questions in 87% of cases (versus 41% under unconstrained generation), while complete empirical manuscripts can be produced at an average API cost of $0.8-$1.5 per run. These results suggest that Human-AI collaborative pipelines may provide a practical path toward scalable empirical research.

This article extends the analysis of Atkinson, Foley, and Ganz in "Beyond the Spoiler Effect: Can Ranked-Choice Voting Solve the Problem of Political Polarization?". Their work uses a one-dimensional spatial model based on survey data from the Cooperative Election Survey (CES) to examine how instant-runoff voting (IRV) and Condorcet methods promote candidate moderation. Their model assumes an idealized electoral environment in which all voters possess complete information regarding candidates' ideological positions, all voters provide complete preference rankings, etc. Under these assumptions, their results indicate that Condorcet methods tend to yield winners who are substantially more moderate than those produced by IRV. We construct new models based on CES data which take into account more realistic voter behavior, such as the presence of partial ballots. Our general finding is that under more realistic models the differences between Condorcet methods and IRV largely disappear, implying that in real-world settings the moderating effect of Condorcet methods may not be nearly as strong as what is suggested by more theoretical models.

A defining feature of digital goods is that replication and degradation are costless: once a high-quality good is produced, low-quality versions can be created and distributed at no additional cost. This paper studies quality-based screening in markets for digital goods. Production costs depend only on the highest quality supplied, unlike in standard screening models. The monopolist allocation exhibits two interdependent inefficiencies. First, a productive inefficiency: the monopolist underinvests in the highest quality relative to the efficiency benchmark. Second, due to a distributional inefficiency, certain buyers receive degraded versions of the produced good. Competition exacerbates productive inefficiency, but improves distributional efficiency.

I study multidimensional sequential screening. A monopolist contracts with a buyer who privately observes information about the distribution of their eventual valuations for multiple goods. After initial private information is reported and the contract is signed, the buyer learns and reports realized valuations. In these settings, the monopolist frontloads surplus extraction: Any information rents given to the buyer to elicit their true valuations can be extracted in expectation before those valuations are drawn, transforming the multidimensional screening problem by distorting buyer information rents compared to static screening. If the buyer's distributions over valuations are commonly FOSD ordered and regular for each good; and satisfy invariant dependencies (valuations can be dependent across goods, but how valuations are coupled cannot vary), the optimal mechanism coincides with independently offering the optimal sequential screening mechanism for each good. This rationalizes membership payments followed by separate sales schemes seen across multiple industries.

We present an algorithm for computing all evolutionarily stable strategies in nondegenerate normal-form games with three or more players.

Discussions of political disagreement emphasize two patterns: polarization, where beliefs diverge toward opposite extremes on each issue dimension; and issue alignment, where individuals' views across issues become more internally consistent. We show that both can simultaneously arise under Bayesian learning from public information. We characterize the public signals that can induce persistent polarization on all dimensions and find that evidence of issue alignment can polarize Bayesian agents. However, we show that even stronger notions of polarization, requiring divergence beyond marginal beliefs, are inconsistent with Bayesian rationality. Whether multidimensional belief polarization translates into divergent aggregate positions depends on cross-issue separability.

We study random utility (RU) rationality with aggregation when the underlying alternatives in each aggregate vary across consumers and are unobserved, as is typical for an outside option. RUM over the underlying alternatives is the natural assumption on the data generating process, while an aggregated random utility model (ARUM) is the standard empirical tool. We characterize RU rationality in three frameworks and show its testable implications are substantially weaker than those of an ARUM. We provide two independent conditions for their equivalence: non-overlapping preferences within aggregates and menu-independent aggregation. Simulations show that violating either condition produces meaningful estimation bias when imposing an ARUM.

This paper analyzes Structural Vector Autoregressions (SVARs) where identification of structural parameters holds locally but not globally. In this case there exists a set of isolated structural parameter points that are observationally equivalent under the imposed restrictions. Although the data do not inform us which observationally equivalent point should be selected, the common frequentist practice is to obtain one as a maximum likelihood estimate and perform impulse response analysis accordingly. For Bayesians, the lack of global identification translates to non-vanishing sensitivity of the posterior to the prior, and the multi-modal likelihood gives rise to computational challenges as posterior sampling algorithms can fail to explore all the modes. This paper overcomes these challenges by proposing novel estimation and inference procedures. We characterize a class of identifying restrictions and circumstances that deliver local but non-global identification, and the resulting number of observationally equivalent parameter values. We propose algorithms to exhaustively compute all admissible structural parameters given reduced-form parameters and utilize them to sample from the multi-modal posterior. In addition, viewing the set of observationally equivalent parameter points as the identified set, we develop Bayesian and frequentist procedures for inference on the corresponding set of impulse responses. An empirical example illustrates our proposal.

This study proposes DisSim-FinBERT, a novel framework that integrates Discourse Simplification (DisSim) with Aspect-Based Sentiment Analysis (ABSA) to enhance sentiment prediction in complex financial texts. By simplifying intricate documents such as Federal Open Market Committee (FOMC) minutes, DisSim improves the precision of aspect identification, resulting in sentiment predictions that align more closely with economic events. The model preserves the original informational content and captures the inherent volatility of financial language, offering a more nuanced and accurate interpretation of long-form financial communications. This approach provides a practical tool for policymakers and analysts aiming to extract actionable insights from central bank narratives and other detailed economic documents.

In this paper we propose a class of structural vector autoregressions (SVARs) characterized by structural breaks (SVAR-WB). Together with standard restrictions on the parameters and on functions of them, we also consider constraints across the different regimes. Such constraints can be either (a) in the form of stability restrictions, indicating that not all the parameters or impulse responses are subject to structural changes, or (b) in terms of inequalities regarding particular characteristics of the SVAR-WB across the regimes. We show that all these kinds of restrictions provide benefits in terms of identification. We derive conditions for point and set identification of the structural parameters of the SVAR-WB, mixing equality, sign, rank and stability restrictions, as well as constraints on forecast error variances (FEVs). As point identification, when achieved, holds locally but not globally, there will be a set of isolated structural parameters that are observationally equivalent in the parametric space. In this respect, both common frequentist and Bayesian approaches produce unreliable inference as the former focuses on just one of these observationally equivalent points, while for the latter on a non-vanishing sensitivity to the prior. To overcome these issues, we propose alternative approaches for estimation and inference that account for all admissible observationally equivalent structural parameters. Moreover, we develop a pure Bayesian and a robust Bayesian approach for doing inference in set-identified SVAR-WBs. Both the theory of identification and inference are illustrated through a set of examples and an empirical application on the transmission of US monetary policy over the great inflation and great moderation regimes.

In a landmark contribution to the structural vector autoregression (SVARs) literature, Rubio-Ramirez, Waggoner, and Zha (2010, `Structural Vector Autoregressions: Theory of Identification and Algorithms for Inference,' Review of Economic Studies) shows a necessary and sufficient condition for equality restrictions to globally identify the structural parameters of a SVAR. The simplest form of the necessary and sufficient condition shown in Theorem 7 of Rubio-Ramirez et al (2010) checks the number of zero restrictions and the ranks of particular matrices without requiring knowledge of the true value of the structural or reduced-form parameters. However, this note shows by counterexample that this condition is not sufficient for global identification. Analytical investigation of the counterexample clarifies why their sufficiency claim breaks down. The problem with the rank condition is that it allows for the possibility that restrictions are redundant, in the sense that one or more restrictions may be implied by other restrictions, in which case the implied restriction contains no identifying information. We derive a modified necessary and sufficient condition for SVAR global identification and clarify how it can be assessed in practice.

Induced order statistics (IOS) arise when sample units are reordered according to the value of an auxiliary variable, and the associated responses are analyzed in that induced order. IOS play a central role in applications where the goal is to approximate the conditional distribution of an outcome at a fixed covariate value using observations whose covariates lie closest to that point, including regression discontinuity designs, k-nearest-neighbor methods, and distributionally robust optimization. Existing asymptotic results allow the dimension of the IOS vector to grow with the sample size only under smoothness conditions that are often too restrictive for practical data-generating processes. In particular, these conditions rule out boundary points, which are central to regression discontinuity designs. This paper develops general convergence rates for IOS under primitive and comparatively weak assumptions. We derive sharp marginal rates for the approximation of the target conditional distribution in Hellinger and total variation distances under quadratic mean differentiability and show how these marginal rates translate into joint convergence rates for the IOS vector. Our results are widely applicable: they rely on a standard smoothness condition and accommodate both interior and boundary conditioning points, as required in regression discontinuity and related settings. In the supplementary appendix, we provide complementary results under a Taylor/Holder remainder condition. Our results reveal a clear trade-off between smoothness and speed of convergence, identify regimes in which Hellinger and total variation distances behave differently, and provide explicit growth conditions on the number of nearest neighbors.

We develop a stochastic macro-financial model in continuous time by integrating two specifications of the Keen economic framework with a financial market driven by a jump-diffusion process. The economic block of the model combines monetary debt-deflation mechanisms with Ponzi-type financial destabilization and is influenced by the financial market through a stochastic interest rate that depends on asset price returns. The financial market block of the model consists of an asset with jump--diffusion price process with endogenous, state-dependent jump intensities driven by speculative credit flows. The model formalizes a feedback loop linking credit expansion, crash risk, perceived return dynamics, and bank lending spreads. Under suitable parameter restrictions, we establish global existence and non-explosion of the coupled system. Numerical experiments illustrate how variations in credit sensitivity and jump parameters generate regimes ranging from stable growth to recurrent boom--bust cycles. The framework provides a tractable setting for analyzing endogenous financial fragility within a mathematically well-posed macro--financial system.

In modern randomized experiments, large-scale data collection increasingly yields rich baseline covariates and auxiliary information from multiple sources. Such information offers opportunities for more precise treatment effect estimation, but it also raises the challenge of integrating heterogeneous information coherently without compromising validity. Covariate-adaptive randomization (CAR) is widely used to improve covariate balance at the design stage, but it typically balances only a small set of covariates used to form strata, making covariate adjustment at the analysis stage essential for more efficient estimation of treatment effects. Beyond standard covariate adjustment, it is often desirable to incorporate auxiliary information, including cross-stratum information, predictions from various machine learning models, and external data from historical trials or real-world sources. While this auxiliary information is widely available, existing covariate adjustment methods under CAR primarily exploit within-stratum covariates and do not provide a coherent mechanism for integrating it. We propose a unified calibration framework that integrates such information through an information proxy vector and calibration weights defined by a convex optimization problem. The resulting estimator recovers many recent covariate adjustment procedures as special cases while providing a systematic mechanism for both internal and external information borrowing within a single framework. We establish large-sample validity and a no-harm efficiency guarantee, showing that incorporating additional information sources cannot increase asymptotic variance, and we extend the theory to settings in which both the number of strata and the number of information sources grow with the sample size.