|
on Econometrics |
| By: | Matias D. Cattaneo; Rocio Titiunik; Ruiqi Rae Yu |
| Abstract: | Boundary Discontinuity Designs are used to learn about treatment effects along a continuous boundary that splits units into control and treatment groups according to a bivariate score variable. These research designs are also called Multi-Score Regression Discontinuity Designs, a leading special case being Geographic Regression Discontinuity Designs. We study the statistical properties of commonly used local polynomial treatment effects estimators along the continuous treatment assignment boundary. We consider two distinct approaches: one based explicitly on the bivariate score variable for each unit, and the other based on their univariate distance to the boundary. For each approach, we present pointwise and uniform estimation and inference methods for the treatment effect function over the assignment boundary. Notably, we show that methods based on univariate distance to the boundary exhibit an irreducible large misspecification bias when the assignment boundary has kinks or other irregularities, making the distance-based approach unsuitable for empirical work in those settings. In contrast, methods based on the bivariate score variable do not suffer from that drawback. We illustrate our methods with an empirical application. Companion general-purpose software is provided. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.05670 |
| By: | AmirEmad Ghassami; James M. Robins; Andrea Rotnitzky |
| Abstract: | In various statistical settings, the goal is to estimate a function which is restricted by the statistical model only through a conditional moment restriction. Prominent examples include the nonparametric instrumental variable framework for estimating the structural function of the outcome variable, and the proximal causal inference framework for estimating the bridge functions. A common strategy in the literature is to find the minimizer of the projected mean squared error. However, this approach can be sensitive to misspecification or slow convergence rate of the estimators of the involved nuisance components. In this work, we propose a debiased estimation strategy based on the influence function of a modification of the projected error and demonstrate its finite-sample convergence rate. Our proposed estimator possesses a second-order bias with respect to the involved nuisance functions and a desirable robustness property with respect to the misspecification of one of the nuisance functions. The proposed estimator involves a hyper-parameter, for which the optimal value depends on potentially unknown features of the underlying data-generating process. Hence, we further propose a hyper-parameter selection approach based on cross-validation and derive an error bound for the resulting estimator. This analysis highlights the potential rate loss due to hyper-parameter selection and underscore the importance and advantages of incorporating debiasing in this setting. We also study the application of our approach to the estimation of regular parameters in a specific parameter class, which are linear functionals of the solutions to the conditional moment restrictions and provide sufficient conditions for achieving root-n consistency using our debiased estimator. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.20787 |
| By: | Marcelo Ortiz-Villavicencio; Pedro H. C. Sant'Anna |
| Abstract: | Triple Differences (DDD) designs are widely used in empirical work to relax parallel trends assumptions in Difference-in-Differences (DiD) settings. This paper shows that common DDD implementations -- such as taking the difference between two DiDs or applying three-way fixed effects regressions -- are generally invalid when identification requires conditioning on covariates. In staggered adoption settings, the common DiD practice of pooling all not-yet-treated units as a comparison group introduces additional bias, even when covariates are not required for identification. These insights challenge conventional empirical strategies and underscore the need for estimators tailored specifically to DDD structures. We develop regression adjustment, inverse probability weighting, and doubly robust estimators that remain valid under covariate-adjusted DDD parallel trends. For staggered designs, we show how to correctly leverage multiple comparison groups to get more informative inference. Simulations highlight substantial bias reductions and precision gains relative to standard approaches, offering a new framework for credible DDD estimation in empirical research. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.09942 |
| By: | Guanhao Zhou; Yuefeng Han; Xiufan Yu |
| Abstract: | This paper studies the task of estimating heterogeneous treatment effects in causal panel data models, in the presence of covariate effects. We propose a novel Covariate-Adjusted Deep Causal Learning (CoDEAL) for panel data models, that employs flexible model structures and powerful neural network architectures to cohesively deal with the underlying heterogeneity and nonlinearity of both panel units and covariate effects. The proposed CoDEAL integrates nonlinear covariate effect components (parameterized by a feed-forward neural network) with nonlinear factor structures (modeled by a multi-output autoencoder) to form a heterogeneous causal panel model. The nonlinear covariate component offers a flexible framework for capturing the complex influences of covariates on outcomes. The nonlinear factor analysis enables CoDEAL to effectively capture both cross-sectional and temporal dependencies inherent in the data panel. This latent structural information is subsequently integrated into a customized matrix completion algorithm, thereby facilitating more accurate imputation of missing counterfactual outcomes. Moreover, the use of a multi-output autoencoder explicitly accounts for heterogeneity across units and enhances the model interpretability of the latent factors. We establish theoretical guarantees on the convergence of the estimated counterfactuals, and demonstrate the compelling performance of the proposed method using extensive simulation studies and a real data application. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.20536 |
| By: | Apoorva Lal; Winston Chou |
| Abstract: | Double Machine Learning is commonly used to estimate causal effects in large observational datasets. The "residuals-on-residuals" regression estimator (RORR) is especially popular for its simplicity and computational tractability. However, when treatment effects are heterogeneous, the proper interpretation of RORR may not be well understood. We show that, for many-valued treatments with continuous dose-response functions, RORR converges to a conditional variance-weighted average of derivatives evaluated at points not in the observed dataset, which generally differs from the Average Causal Derivative (ACD). Hence, even if all units share the same dose-response function, RORR does not in general converge to an average treatment effect in the population represented by the sample. We propose an alternative estimator suitable for large datasets. We demonstrate the pitfalls of RORR and the favorable properties of the proposed estimator in both an illustrative numerical example and an application to real-world data from Netflix. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.07462 |
| By: | Eli Ben-Michael |
| Abstract: | Many important quantities of interest are only partially identified from observable data: the data can limit them to a set of plausible values, but not uniquely determine them. This paper develops a unified framework for covariate-assisted estimation, inference, and decision making in partial identification problems where the parameter of interest satisfies a series of linear constraints, conditional on covariates. In such settings, bounds on the parameter can be written as expectations of solutions to conditional linear programs that optimize a linear function subject to linear constraints, where both the objective function and the constraints may depend on covariates and need to be estimated from data. Examples include estimands involving the joint distributions of potential outcomes, policy learning with inequality-aware value functions, and instrumental variable settings. We propose two de-biased estimators for bounds defined by conditional linear programs. The first directly solves the conditional linear programs with plugin estimates and uses output from standard LP solvers to de-bias the plugin estimate, avoiding the need for computationally demanding vertex enumeration of all possible solutions for symbolic bounds. The second uses entropic regularization to create smooth approximations to the conditional linear programs, trading a small amount of approximation error for improved estimation and computational efficiency. We establish conditions for asymptotic normality of both estimators, show that both estimators are robust to first-order errors in estimating the conditional constraints and objectives, and construct Wald-type confidence intervals for the partially identified parameters. These results also extend to policy learning problems where the value of a decision policy is only partially identified. We apply our methods to a study on the effects of Medicaid enrollment. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.12215 |
| By: | Arkadiusz Szyd{\l}owski |
| Abstract: | We propose tests for the convexity/linearity/concavity of a transformation of the dependent variable in a semiparametric transformation model. These tests can be used to verify monotonicity of the treatment effect, or, equivalently, concavity/convexity of the outcome with respect to the treatment, in (quasi-)experimental settings. Our procedure does not require estimation of the transformation or the distribution of the error terms, thus it is easy to implement. The statistic takes the form of a U statistic or a localised U statistic, and we show that critical values can be obtained by bootstrapping. In our application we test the convexity of loan demand with respect to the interest rate using experimental data from South Africa. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.08914 |
| By: | Ludgero Glorias; Federico Martellosio; J. M. C. Santos Silva |
| Abstract: | We consider two nonparametric approaches to ensure that instrumental variables estimators of a linear equation satisfy the rich-covariates condition emphasized by Blandhol et al. (2025), even when the instrument is not unconditionally randomly assigned and the model is not saturated. Both approaches start with a nonparametric estimate of the expectation of the instrument conditional on the covariates, and ensure that the rich-covariates condition is satisfied either by using as the instrument the difference between the original instrument and its estimated conditional expectation, or by adding the estimated conditional expectation to the set of regressors. We derive asymptotic properties of our instrumental variables estimators, and assess their finite sample performance relative to existing approaches using Monte Carlo simulations. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.21213 |
| By: | Luis Alvarez; Bruno Ferman |
| Abstract: | We study how inference methods for settings with few treated units that rely on treatment effect homogeneity extend to alternative inferential targets when treatment effects are heterogeneous -- namely, tests of sharp null hypotheses, inference on realized treatment effects, and prediction intervals. We show that inference methods for these alternative targets are deeply interconnected: they are either equivalent or become equivalent under additional assumptions. Our results show that methods designed under treatment effect homogeneity can remain valid for these alternative targets when treatment effects are stochastic, offering new theoretical justifications and insights on their applicability. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.14998 |
| By: | Holger Dette; Kathrin M\"ollenhoff; Dominik Wied |
| Abstract: | In the framework of semiparametric distribution regression, we consider the problem of comparing the conditional distribution functions corresponding to two samples. In contrast to testing for exact equality, we are interested in the (null) hypothesis that the $L^2$ distance between the conditional distribution functions does not exceed a certain threshold in absolute value. The consideration of these hypotheses is motivated by the observation that in applications, it is rare, and perhaps impossible, that a null hypothesis of exact equality is satisfied and that the real question of interest is to detect a practically significant deviation between the two conditional distribution functions. The consideration of a composite null hypothesis makes the testing problem challenging, and in this paper we develop a pivotal test for such hypotheses. Our approach is based on self-normalization and therefore requires neither the estimation of (complicated) variances nor bootstrap approximations. We derive the asymptotic limit distribution of the (appropriately normalized) test statistic and show consistency under local alternatives. A simulation study and an application to German SOEP data reveal the usefulness of the method. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.06545 |
| By: | Zhehao Zhang; Thomas S. Richardson |
| Abstract: | Individual treatment effect (ITE) is often regarded as the ideal target of inference in causal analyses and has been the focus of several recent studies. In this paper, we describe the intrinsic limits regarding what can be learned concerning ITEs given data from large randomized experiments. We consider when a valid prediction interval for the ITE is informative and when it can be bounded away from zero. The joint distribution over potential outcomes is only partially identified from a randomized trial. Consequently, to be valid, an ITE prediction interval must be valid for all joint distribution consistent with the observed data and hence will in general be wider than that resulting from knowledge of this joint distribution. We characterize prediction intervals in the binary treatment and outcome setting, and extend these insights to models with continuous and ordinal outcomes. We derive sharp bounds on the probability mass function (pmf) of the individual treatment effect (ITE). Finally, we contrast prediction intervals for the ITE and confidence intervals for the average treatment effect (ATE). This also leads to the consideration of Fisher versus Neyman null hypotheses. While confidence intervals for the ATE shrink with increasing sample size due to its status as a population parameter, prediction intervals for the ITE generally do not vanish, leading to scenarios where one may reject the Neyman null yet still find evidence consistent with the Fisher null, highlighting the challenges of individualized decision-making under partial identification. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.07469 |
| By: | Jiawei Fu; Donald P. Green |
| Abstract: | How should we analyze randomized experiments in which the main outcome is measured in multiple ways and each measure contains some degree of error? Since Costner (1971) and Bagozzi (1977), methodological discussions of experiments with latent outcomes have reviewed the modeling assumptions that are invoked when the quantity of interest is the average treatment effect (ATE) of a randomized intervention on a latent outcome that is measured with error. Many authors have proposed methods to estimate this ATE when multiple measures of an outcome are available. Despite this extensive literature, social scientists rarely use these modeling approaches when analyzing experimental data, perhaps because the surge of interest in experiments coincides with increased skepticism about the modeling assumptions that these methods invoke. The present paper takes a fresh look at the use of latent variable models to analyze experiments. Like the skeptics, we seek to minimize reliance on ad hoc assumptions that are not rooted in the experimental design and measurement strategy. At the same time, we think that some of the misgivings that are frequently expressed about latent variable models can be addressed by modifying the research design in ways that make the underlying assumptions defensible or testable. We describe modeling approaches that enable researchers to identify and estimate key parameters of interest, suggest ways that experimental designs can be augmented so as to make the modeling requirements more credible, and discuss empirical tests of key modeling assumptions. Simulations and an empirical application illustrate the gains in terms of precision and robustness. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.21909 |
| By: | Stéphane Bonhomme; Kevin Dano; Bryan S. Graham |
| Abstract: | Many panel data methods, while allowing for general dependence between covariates and time-invariant agent-specific heterogeneity, place strong a priori restrictions on feedback: how past outcomes, covariates, and heterogeneity map into future covariate levels. Ruling out feedback entirely, as often occurs in practice, is unattractive in many dynamic economic settings. We provide a general characterization of all feedback and heterogeneity robust (FHR) moment conditions for nonlinear panel data models and present constructive methods to derive feasible moment based estimators for specific models. We also use our moment characterization to compute semiparametric efficiency bounds, allowing for a quantification of the information loss associated with accommodating feedback, as well as providing insight into how to construct estimators with good efficiency properties in practice. Our results apply both to the finite dimensional parameter indexing the parametric part of the model as well as to estimands that involve averages over the distribution of unobserved heterogeneity. We illustrate our methods by providing a complete characterization of all FHR moment functions in the multi-spell mixed proportional hazards model. We compute efficient moment functions for both model parameters and average effects in this setting. |
| Date: | 2025–06–20 |
| URL: | https://d.repec.org/n?u=RePEc:azt:cemmap:12/25 |
| By: | Iacone, Fabrizio; Taylor, AM Robert |
| Abstract: | We propose a nonparametric portmanteau test for detecting changes in the unconditional mean of a univariate time series which may display either long or short memory. Our approach is designed to have power against, among other things, cases where the mean component of the series displays abrupt level shifts, deterministic trending behaviour, or is subject to some form of time-varying, continuous change. The test we propose is simple to compute, being based on ratios of periodogram ordinates, has a pivotal limiting null distribution of known form which reduces to the multiple of a χ²₂ random variable in the case where the series is short memory, and has power against a wide class of time-varying mean models. A Monte Carlo simulation study into the finite sample behaviour of the test shows it to have both good size properties under the null for a range of long and short memory series and to exhibit good power against a variety of plausible time-varying mean alternatives. Because of its simplicity, we recommend our periodogram ratio test as a routine portmanteau test for whether the mean component of a time series can reasonably be treated as constant. |
| Date: | 2025–06–19 |
| URL: | https://d.repec.org/n?u=RePEc:esy:uefcwp:41128 |
| By: | Olakunle, Kayode; Owolabi, Abiola T.; Olatayo, Timothy O. |
| Abstract: | This study builds upon the idea of a ridge-type estimator originally designed for linear regression models, adapting it for use in Poisson regression to effectively address multicollinearity in count data. A simulation-based evaluation of various estimators under multicollinearity is presented. The simulation results, shown for cases where p=2 and p=4, highlight the Mean Square Error (MSE) values for each estimator, identifying the best-performing estimators under different scenarios. The findings emphasize the limitations of the existing Poisson Maximum Likelihood Estimator (PMLE), which consistently demonstrates instability and poor performance in the presence of multicollinearity. In contrast, the newly proposed Poisson New Ridge-Type (PNRT) estimators show superior performance. Among the PNRT variants, the estimator using the median biasing parameter consistently achieves the lowest MSE. The simulations also reveal that larger sample sizes reduce MSE values, indicating improved estimator efficiency. Moreover, higher correlation coefficients (ρ = 0.99) lead to increased MSE, whereas moderate correlations (ρ = 0.75) result in more stable and lower error values. Overall, the PNRT variants demonstrate the lowest MSEs, confirming that lower MSE corresponds to better estimator performance, even under severe multicollinearity. |
| Keywords: | Multicollinearity, Mean Square Error, Estimator, Poisson Regression Model |
| Date: | 2025 |
| URL: | https://d.repec.org/n?u=RePEc:zbw:esrepo:319678 |
| By: | Lukas Bauer; Ekaterina Kazak |
| Abstract: | This paper proposes a Conditional Method Confidence Set (CMCS) which allows to select the best subset of forecasting methods with equal predictive ability conditional on a specific economic regime. The test resembles the Model Confidence Set by Hansen et al. (2011) and is adapted for conditional forecast evaluation. We show the asymptotic validity of the proposed test and illustrate its properties in a simulation study. The proposed testing procedure is particularly suitable for stress-testing of financial risk models required by the regulators. We showcase the empirical relevance of the CMCS using the stress-testing scenario of Expected Shortfall. The empirical evidence suggests that the proposed CMCS procedure can be used as a robust tool for forecast evaluation of market risk models for different economic regimes. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.21278 |
| By: | Mengqi Li |
| Abstract: | This paper studies the identification of the average treatment effect on the treated (ATT) under unconfoundedness when covariate overlap is partial. A formal diagnostic is proposed to characterize empirical support -- the subset of the covariate space where ATT is point-identified due to the presence of comparable untreated units. Where support is absent, standard estimators remain computable but cease to identify meaningful causal parameters. A general sensitivity framework is developed, indexing identified sets by curvature constraints on the selection mechanism. This yields a structural selection frontier tracing the trade-off between assumption strength and inferential precision. Two diagnostic statistics are introduced: the minimum assumption strength for sign identification (MAS-SI), and a fragility index that quantifies the minimal deviation from ignorability required to overturn qualitative conclusions. Applied to the LaLonde (1986) dataset, the framework reveals that nearly half the treated strata lack empirical support, rendering the ATT undefined in those regions. Simulations confirm that ATT estimates may be stable in magnitude yet fragile in epistemic content. These findings reframe overlap not as a regularity condition but as a prerequisite for identification, and recast sensitivity analysis as integral to empirical credibility rather than auxiliary robustness. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.08950 |
| By: | Zhixin Wang; Zhengyu Zhang |
| Abstract: | The partial effect refers to the impact of a change in a target variable D on the distribution of an outcome variable Y . This study examines the identification and inference of a wide range of partial effects at the threshold in the sharp regression kink (RK) design under general policy interventions. We establish a unifying framework for conducting inference on the effect of an infinitesimal change in D on smooth functionals of the distribution of Y, particularly when D is endogenous and instrumental variables are unavailable. This framework yields a general formula that clarifies the causal interpretation of numerous existing sharp RK estimands in the literature. We develop the relevant asymptotic theory, introduce a multiplier bootstrap procedure for inference, and provide practical implementation guidelines. Applying our method to the effect of unemployment insurance (UI) benefits on unemployment duration, we find that while higher benefits lead to longer durations, they also tend to reduce their dispersion. Furthermore, our results show that the magnitude of the partial effect can change substantially depending on the specific form of the policy intervention. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.11663 |
| By: | Zhixin Wang; Yu Zhang; Zhengyu Zhang |
| Abstract: | This paper investigates the structural interpretation of the marginal policy effect (MPE) within nonseparable models. We demonstrate that, for a smooth functional of the outcome distribution, the MPE equals its functional derivative evaluated at the outcome-conditioned weighted average structural derivative. This equivalence is definitional rather than identification-based. Building on this theoretical result, we propose an alternative identification strategy for the MPE that complements existing methods. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.11694 |
| By: | Yang Xu |
| Abstract: | This paper studies a linear production model in team networks with missing links. In the model, heterogeneous workers, represented as nodes, produce jointly and repeatedly within teams, represented as links. Links are omitted when their associated outcome variables fall below a threshold, resulting in partial observability of the network. To address this, I propose a Generalized Method of Moments estimator under normally distributed errors and develop a distribution-free test for detecting link truncation. Applied to academic publication data, the estimator reveals and corrects a substantial downward bias in the estimated scaling factor that aggregates individual fixed effects into team-specific fixed effects. This finding suggests that the collaboration premium may be systematically underestimated when missing links are not properly accounted for. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.08405 |
| By: | Dimitris Korobilis |
| Abstract: | I introduce a high-dimensional Bayesian vector autoregressive (BVAR) framework designed to estimate the effects of conventional monetary policy shocks. The model captures structural shocks as latent factors, enabling computationally efficient estimation in high-dimensional settings through a straightforward Gibbs sampler. By incorporating time variation in the effects of monetary policy while maintaining tractability, the methodology offers a flexible and scalable approach to empirical macroeconomic analysis using BVARs, well-suited to handle data irregularities observed in recent times. Applied to the U.S. economy, I identify monetary shocks using a combination of high-frequency surprises and sign restrictions, yielding results that are robust across a wide range of specification choices. The findings indicate that the Federal Reserve's influence on disaggregated consumer prices fluctuated significantly during the 2022-24 high-inflation period, shedding new light on the evolving dynamics of monetary policy transmission. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.06649 |
| By: | Zhentao Shi; Jin Xi; Haitian Xie |
| Abstract: | This paper investigates the use of synthetic control methods for causal inference in macroeconomic settings when dealing with possibly nonstationary data. While the synthetic control approach has gained popularity for estimating counterfactual outcomes, we caution researchers against assuming a common nonstationary trend factor across units for macroeconomic outcomes, as doing so may result in misleading causal estimation-a pitfall we refer to as the spurious synthetic control problem. To address this issue, we propose a synthetic business cycle framework that explicitly separates trend and cyclical components. By leveraging the treated unit's historical data to forecast its trend and using control units only for cyclical fluctuations, our divide-and-conquer strategy eliminates spurious correlations and improves the robustness of counterfactual prediction in macroeconomic applications. As empirical illustrations, we examine the cases of German reunification and the handover of Hong Kong, demonstrating the advantages of the proposed approach. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.22388 |
| By: | Leonard Goff; Eric Mbakop |
| Abstract: | This paper studies inference on the value of a linear program (LP) when both the objective function and constraints are possibly unknown and must be estimated from data. We show that many inference problems in partially identified models can be reformulated in this way. Building on Shapiro (1991) and Fang and Santos (2019), we develop a pointwise valid inference procedure for the value of an LP. We modify this pointwise inference procedure to construct one-sided inference procedures that are uniformly valid over large classes of data-generating processes. Our results provide alternative testing procedures for problems considered in Andrews et al. (2023), Cox and Shi (2023), and Fang et al. (2023) (in the low-dimensional case), and remain valid when key components--such as the coefficient matrix--are unknown and must be estimated. Moreover, our framework also accommodates inference on the identified set of a subvector, in models defined by linear moment inequalities, and does so under weaker constraint qualifications than those in Gafarov (2025). |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.06776 |
| By: | Hyeon-seung Huh (Yonsei University); David Kim (University of Sydney) |
| Abstract: | In the sign-identified Bayesian SVAR model, the standard setup usually postulates a Haar prior for the rotation matrix. However, the rotation matrix does not enter the likelihood, and its prior is never updated by data. A key implication is that the Haar prior rotation matrix can be unintentionally informative about posterior inference, despite having no relationship with economic interpretations or data. We show empirically how Haar prior rotation matrix could affect the results in the context of two well-known models: Baumeister and Hamilton (2018) and Peersman and Straub (2004, 2009). For both models, the histograms of accepted impact responses are shown to reflect closely the histograms of accepted rotation matrices. Although sampling uncertainty is updated by the data, it barely contributes to determining the set of accepted impact responses compared to the uncertainty about the rotation matrix, explaining why the histograms between the accepted impact responses and the accepted rotation matrices are similar in shape. To a lesser extent, the influence of the rotation matrix is carried over to subsequent responses where additional sampling uncertainty arises. Our results reinforce the argument that the rotation prior can affect the distribution of accepted responses, possibly leading to erroneous inferences. |
| Keywords: | Structural vector autoregressions, Sign restrictions, Haar prior, Rotation matrix, Informativeness |
| JEL: | C32 C36 C51 E32 E52 |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:yon:wpaper:2025rwp-246 |
| By: | Jesse Zhou; Geoffrey T. Wodtke |
| Abstract: | Analyses of causal mediation often involve exposure-induced confounders or, relatedly, multiple mediators. In such applications, researchers aim to estimate a variety of different quantities, including interventional direct and indirect effects, multivariate natural direct and indirect effects, and/or path-specific effects. This study introduces a general approach to estimating all these quantities by simulating potential outcomes from a series of distribution models for each mediator and the outcome. Building on similar methods developed for analyses with only a single mediator (Imai et al. 2010), we first outline how to implement this approach with parametric models. The parametric implementation can accommodate linear and nonlinear relationships, both continuous and discrete mediators, and many different types of outcomes. However, it depends on correct specification of each model used to simulate the potential outcomes. To address the risk of misspecification, we also introduce an alternative implementation using a novel class of nonparametric models, which leverage deep neural networks to approximate the relevant distributions without relying on strict assumptions about functional form. We illustrate both methods by reanalyzing the effects of media framing on attitudes toward immigration (Brader et al. 2008) and the effects of prenatal care on preterm birth (VanderWeele et al. 2014). |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.14019 |
| By: | Sofia Velasco |
| Abstract: | This article proposes a novel framework that integrates Bayesian Additive Regression Trees (BART) into a Factor-Augmented Vector Autoregressive (FAVAR) model to forecast macro-financial variables and examine asymmetries in the transmission of oil price shocks. By employing nonparametric techniques for dimension reduction, the model captures complex, nonlinear relationships between observables and latent factors that are often missed by linear approaches. A simulation experiment comparing FABART to linear alternatives and a Monte Carlo experiment demonstrate that the framework accurately recovers the relationship between latent factors and observables in the presence of nonlinearities, while remaining consistent under linear data-generating processes. The empirical application shows that FABART substantially improves forecast accuracy for industrial production relative to linear benchmarks, particularly during periods of heightened volatility and economic stress. In addition, the model reveals pronounced sign asymmetries in the transmission of oil supply news shocks to the U.S. economy, with positive shocks generating stronger and more persistent contractions in real activity and inflation than the expansions triggered by negative shocks. A similar pattern emerges at the U.S. federal state level, where negative shocks lead to modest declines in employment compared to the substantially larger contractions observed after positive shocks. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.11551 |
| By: | Jan Ditzen; Ovidijus Stauskas |
| Abstract: | Information criteria (IC) are important tools in the literature of factor models that allow one to estimate a typically unknown number of latent factors. Although first proposed for the Principal Components setting in the seminal work by Bai and Ng (2002), it has recently been shown that IC perform extremely well in Common Correlated Effects (CCE) and related setups with stationary factors. In particular, they can consistently select a sufficient set of cross-section averages (CAs) to approximate the factor space. Given that CAs can proxy nonstationary factors, it is tempting to believe that the consistency of IC continues to hold under such generality. This study is a cautionary tale for practitioners. We demonstrate formally and in simulations that IC has a severe underselection issue even under very mild forms of factor non-stationarity, which goes against the sentiment in the CAs literature. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.08615 |
| By: | Hyeon-seung Huh (Yonsei University); David Kim (University of Sydney) |
| Abstract: | The use of sign restrictions to identify monetary policy shocks in structural vector autoregression (SVAR) models has garnered significant attention in recent years. In this context, we revisit two influential studies—Uhlig (2005) and Arias et al. (2019)—which offer conflicting conclusions regarding the output effects of contractionary monetary policy shocks. Our analysis seeks to uncover the underlying causes of these discrepancies and evaluate the sensitivity of the results to alternative model specifications. Specifically, we examine four key factors: (i) the influence of rotation priors on posterior inference in sign-restricted SVAR models, (ii) the robustness of findings when employing an alternative algorithm to generate large sets of responses, (iii) the sensitivity of results to variations in identifying restrictions, and (iv) the robustness of conclusions to changes in the monetary policy equation and the inclusion of the Great Moderation. |
| Keywords: | Sign restrictions, Rotation matrix, monetary policy shocks, Structural vectorvautoregression, Baumeister and Hamilton critique |
| JEL: | C32 C51 E32 E52 |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:yon:wpaper:2025rwp-245 |