This paper proposes a new mixed vector autoregression (MVAR) model to examine the relationship between aggregate time series and functional variables in a multivariate setting. The model facilitates a reexamination of the oil-stock price nexus by estimating the effects of demand and supply shocks from the global market for crude oil on the entire distribution of U.S. stock returns since the late 1980s. We show that the MVAR effectively extracts information from the returns distribution that is more relevant for understanding the oil-stock price nexus beyond simply looking at the first few moments. Using novel functional impulse response functions (FIRFs), we find that oil market demand shocks tend to increase returns, while both demand and supply shocks reduce volatility, and have an asymmetric effect on the returns distribution as a whole. In a value-at-risk (VaR) analysis, we also find that the oil market contains important information that reduces expected loss, and that the response of VaR to the oil market demand and supply shocks has changed over time.
Traditional dynamic discrete choice model-Conditional Choice Probability estimator (DDCM-CCP) literature considered identification using the likelihood of longitudinal choice only. However, such an approach has a limitation in identifying flexible dynamics for latent state due to the discrete and typically small-dimensional nature of choice. This paper extends this literature to utilize imperfect measurements, called proxies, for a latent discrete state. I first show that proxies improve identification and discuss how survey design on proxies affects identification conditions. I then extend the estimator from Arcidiacono and Miller (2011) to pool information from an unbalanced panel of noisy proxies, enabling estimation of more flexible latent state dynamics than Markov chains. As an application, I estimate a dynamic model of labor supply and mental health, where dynamic mental health only imperfectly observed-plays a central role. The results reveal more complex dynamics than a standard Markov chain.
This paper studies approximation error in the quasilinear utility model. Error arises because individuals do not perfectly optimize, and instead satisfice. We investigate the consequences of individual satisficing for modeling aggregate demand, providing an approximate aggregation theorem. We present a simple method for statistical inference on the minimal level of satisficing needed to explain aggregate data. In an illustrative application to scanner panel data, we find that individual-level data require a nontrivial degree of satisficing, but aggregate data admit a representative agent that maximizes a quasilinear utility function.
Linear factor models are generally not identified. We provide sufficient conditions for identification: Under a natural sparsity assumption (the presence of local factors that affect only subsets of observables), the true loading matrix is the sparsest rotation and can be recovered by minimizing the & ell; 1-norm of the loading matrix. This enables economically meaningful interpretation of the individual factors. More generally, our & ell; 1-rotation criterion offers a novel approach to simplify the loading matrix and performs well relative to existing methods (e.g., Varimax, Kaiser (1958)) in our simulations. We illustrate our method in two economic applications. The R package l1rotation implements the method and facilitates adoption.
I build a model of many-to-one matching with nontransferable utility involving many agents on both sides of the market, for example, workers and firms. Under parsimonious assumptions on preferences and assuming that matches are stable, I provide a tractable asymptotic characterization of the joint distribution of match characteristics. I find that one can identify the joint surplus of a match, but cannot separately identify workers' and firms' preferences from data on realized matches. Within-firm variation in matched worker characteristics, only available in many-to-one matching data, can help identifying and estimating unobserved firm heterogeneity in the surplus function.
We show that U.S. shale oil producers exhibit a high degree of short-run price responsiveness, primarily through the timing of well completions and refracturing. Using a novel monthly well-level panel covering over 120,000 shale wells across ten states from 2005 to 2019, we document significant supply adjustments to price signals. The response varies significantly across states and firm types, highlighting the importance of accounting for micro-level heterogeneity in production behavior. Mechanisms include accelerating completion of drilled but uncompleted wells and refracturing older wells when forward-looking price signals are favorable. These findings challenge the common assumption of short-run supply inelasticity and call for oil market models that incorporate operational flexibility and forward-looking behavior of shale oil producers.
This paper studies income inequality and optimal taxation policies in a talent-to-task assignment model of self-selection. Our model considers relative capital-skill complementarities across tasks, leading to the polarization of capital and technology by task complexity, which in turn drives the polarization of job and wage growth by talent levels. Regarding optimal tax policy, the wage compression channel remains effective through the trickle-down effect of subsidizing high-wage earners and taxing low-wage earners. Yet, the wage compression channel via capital, corporate, and R&D taxes, aimed at reducing wage inequality, does not operate via a trickle-down effect. Instead, it works by taxing capital income and R&D investments in high-task-complexity sectors while subsidizing those in low-task-complex sectors. Moreover, we identify a Pigouvian effect that arises to address spillovers, which modifies the marginal tax rates on labor income, capital income, firm profits, and R&D investments.
This paper develops a framework to address issues of contamination in parent-reported measures of child noncognitive skills. We estimate a dynamic model in which child and parental skills evolve jointly and leverage information provided by teachers and interviewers to deal with contamination of parent-reported measures. The model also allows us to examine the relative importance of mothers and fathers in the evolution of child skills. Our findings reveal that ignoring contamination significantly underestimates the role of maternal non-cognitive skills in the evolution of child noncognitive skills. Additionally, we find evidence of stronger feedback effects from child skills to mothers than fathers. Simulation exercises demonstrate how contamination can distort evaluations of early childhood policies, underscoring the importance of robust measurement approaches.
This study uses sociometric data to show that social connections in the classroom shape the diffusion of the negative externalities on cognitive achievement generated by abused and neglected peers. We find the strongest negative effects for students who are socially closest to the abused and neglected peer. The fade-out rate of the negative externality is such that being three peers away from an abused and neglected peer is equivalent to having no such peers. Although the inverse effect-distance relation applies to both verbal and numeric ability, it is conferred through different mechanisms. The abused and neglected peer's lower verbal ability harms her friends' verbal ability, whereas it is the disruptiveness itself that harms classmates' numeric ability.
We introduce a novel approach to solving dynamic programming problems, such as those in many economic models, on a quantum annealer, a specialized device that performs combinatorial optimization. Quantum annealers attempt to solve an NP-hard problem by starting in a quantum superposition of all states and generating candidate global solutions in milliseconds, irrespective of problem size. Using existing quantum hardware, we achieve an order-of-magnitude speed-up in solving the real business cycle model over benchmarks in the literature. We also provide a detailed introduction to quantum annealing and discuss its potential use for more challenging economic problems.
We provide a comprehensive examination of the predictive performance of panel forecasting methods based on individual, pooling, fixed effects, and empirical Bayes estimation, and propose optimal weights for forecast combination schemes. We consider linear panel data models, allowing for weakly exogenous regressors and correlated heterogeneity. We quantify the gains from exploiting panel data and demonstrate how forecasting performance depends on the degree of parameter heterogeneity, whether such heterogeneity is correlated with the regressors, the goodness of fit of the model, and the dimensions of the data. Monte Carlo simulations and empirical applications to house prices and CPI inflation show that empirical Bayes and forecast combination methods perform best overall and rarely produce the least accurate forecasts for individual series.
This paper considers the theoretical, computational, and econometric properties of continuous time dynamic discrete choice games with stochastically sequential moves, introduced by Arcidiacono, Bayer, Blevins, and Ellickson (2016). We consider identification of the rate of move arrivals, which was assumed to be known in previous work, as well as a generalized version with heterogeneous move arrival rates. We re-establish conditions for existence of a Markov perfect equilibrium in the generalized model and consider identification of the model primitives with only discrete time data sampled at fixed intervals. Three foundational example models are considered: a single agent renewal model, a dynamic entry and exit model, and a quality ladder model. Through these examples we examine the computational and statistical properties of estimators via Monte Carlo experiments and an empirical example using data from Rust (1987). The experiments show how parameter estimates behave when moving from continuous time data to discrete time data of decreasing frequency and the computational feasibility as the number of firms grows. The empirical example highlights the impact of allowing decision rates to vary.
An efficient, reliable, and interpretable global solution method, the Deep learning-based algorithm for Heterogeneous Agent Models (DeepHAM), is proposed for solving high dimensional heterogeneous agent models with aggregate shocks. The state distribution is approximately represented by a set of optimal generalized moments. Deep neural networks are used to approximate the value and policy functions, and the objective is optimized over directly simulated paths. In addition to being an accurate global solver, this method has three additional features. First, it is computationally efficient in solving complex heterogeneous agent models, and it does not suffer from the curse of dimensionality. Second, it provides a general and interpretable representation of the distribution over individual states, which is crucial in addressing the classical question of whether and how heterogeneity matters in macroeconomics. Third, it solves the constrained efficiency problem as easily as it solves the competitive equilibrium, which opens up new possibilities for studying optimal monetary and fiscal policies in heterogeneous agent models with aggregate shocks.
We propose a new unified framework for causal inference when outcomes depend on how agents are linked in a social or economic network. Such network interference describes a large literature on treatment spillovers, social interactions, social learning, information diffusion, social capital formation, and more. Our approach works by first characterizing how an agent is linked in the network using the configuration of other agents and connections nearby as measured by path distance. The impact of a policy or treatment assignment is then learned by pooling outcome data across similarly configured agents. In the paper, we propose a new nonparametric modeling approach and consider two applications to causal inference. The first application is to testing policy irrelevance/no treatment effects. The second application is to estimating policy effects/treatment response. We conclude by evaluating the finite-sample properties of our estimation and inference procedures via simulation.
We quantify the aggregate implications and distributional consequences of asymmetric information, focusing on the car market. Private information introduces a lemons penalty, a wedge between the sale price and average quality in the population. We estimate an equilibrium model of car ownership with private information using Danish linked registry data on car ownership, income and wealth. In the first year of ownership, the lemons penalty is 11% of the price. The penalty declines sharply with the length of ownership. The penalty leads to large reductions in transaction volumes and in the rate of turnover of cars. But the market does not collapse: income shocks induce individuals to sell their cars, even if of good quality, and this limits the lemons problem. The size of the lemons penalty declines when income uncertainty in the economy increases, as happens in recessions.
This paper considers optimal taxation of housing capital. To this end, we employ a life-cycle model calibrated to the U.S. economy, where asset holdings and labor productivity vary across households, and tax reforms lead to changes in house and rental prices, interest rates, and wages. We find that the optimal property tax in the long run is considerably higher than today, partly due to the relatively inelastic demand and supply of housing. A higher property tax also reduces house prices and causes a reallocation from housing to business capital, which in turn decreases interest rates and increases wages. These equilibrium effects allow for an improved consumption smoothing over the life cycle. However, most current households would incur substantial welfare losses from an implementation of a higher property tax, since house prices fall, and a majority own their home. Hence, when accounting for transitional dynamics, it is not clear that a higher property tax is feasible or preferred.
This paper develops a world economy HANK model for the Euro Area (EA) Core and Periphery, which captures key features of EA cross- and within-country heterogeneity, to study debt target reforms. We show that fiscal consolidation under the current EA institutional arrangements is quite costly across and within countries, particularly affecting households in the Periphery. Reforming the EA debt targets closer to their historical values can significantly mitigate these welfare losses and make fiscal consolidation more affordable for households in the Periphery. Surprisingly, Core's fiscal expansion to facilitate Periphery's consolidation would not benefit most households in the Periphery, as it would reduce its household income and consumption due to decreased international competitiveness of periphery produced goods. Potential cross-country fiscal externalities could increase the benefits of national fiscal reforms, especially for poor-wealth households. Finally, we find that the welfare-maximizing EA-wide debt target lies between the member states' current debt-to-output ratios.
This paper uses a tractable stochastic integrated-assessment model to analyze the influence of climate change on asset returns across time and maturity. Quasi-analytical, or recursive, formulas allow to price various long-dated assets, including fixed-income products, derivatives, and equities. We find that climate risks will increasingly drive down long-term risk-free yields, reducing them by about 30 basis points by the end of the century. This decline reflects weaker growth and increased uncertainty, leading to a rise in precautionary savings. We illustrate the concept of climate risk premiums by examining model-implied prices of long-term assets vulnerable to sea level rise or temperatures. Climate risk premiums are particularly sensitive to damage assumptions.
We develop new econometric methods for estimation and inference in high-dimensional panel data models with interactive fixed effects. Our approach can be regarded as a nontrivial extension of the very popular common correlated effects (CCE) approach. Roughly speaking, we proceed as follows: We first construct a projection device to eliminate the unobserved factors from the model by applying a dimensionality reduction transform to the matrix of cross-sectionally averaged covariates. The unknown parameters are then estimated by applying lasso techniques to the projected model. For inference purposes, we derive a desparsified version of our lasso-type estimator. While the original CCE approach is restricted to the low-dimensional case where the number of regressors is small and fixed, our methods can deal with both low- and high-dimensional situations where the number of regressors is large and may even exceed the overall sample size. We derive theory for our estimation and inference methods both in the large-T-case, where the time-series length T tends to infinity, and in the small-T-case, where T is a fixed natural number. Specifically, we derive the convergence rate of our estimator and show that its desparsified version is asymptotically normal under suitable regularity conditions. The theoretical analysis of the paper is complemented by a simulation study and an empirical application to characteristic based asset pricing.
