olley-pakes decomposition

This study investigates the causes of Japan’s prolonged stagnation in average wages since the mid-1990s. Leveraging data from 1980 to 2024, it innovatively combines an extended Olley-Pakes decomposition with multidimensional shift-share analysis to decompose real hourly wage growth into four components: demographic changes, employment reallocation across jobs, inter-job relative wage shifts, and within-job wage growth, while distinguishing between employment reallocation and wage structure effects. The findings reveal that all components contributed negatively during 1996–2014: although within-job wages continued to rise, this increase was substantially offset by multidimensional employment shifts—particularly population aging and the expansion of non-regular employment—demonstrating that wage stagnation stems from structural forces rather than any single factor.

This study addresses the limitations of the traditional AKM wage decomposition, which relies on linear covariate adjustments and struggles to accurately disentangle the contributions of worker, firm, and match effects to wage dispersion. The authors propose a generalized AKM framework that retains the variance-component structure while incorporating unknown smooth covariate functions and group-specific nonlinear interaction effects, thereby overcoming the linearity constraint. Their approach achieves, for the first time, consistent and asymptotically normal nonparametric covariate adjustment in the presence of high-dimensional fixed effects and heteroskedastic errors, and establishes the stronger smoothness conditions required for quadratic-form estimation. Application to Portuguese employer-employee data reveals that, after controlling for worker and firm characteristics, the variance shares attributable to worker, firm, and match effects decline to 0.474, 0.121, and 0.047, respectively, with results exhibiting greater sensitivity to the choice of control variables than to functional form specifications.

Comparative statics of technological change in multidimensional assignment models—under general production functions and input distributions—has remained an open problem. Method: This paper introduces a novel orthogonal decomposition framework that uniquely decomposes any technology shift into a gradient component (capturing changes in marginal returns, governed by a Poisson equation) and a divergence-free component (representing labor reallocation). Integrating vector field decomposition, multidimensional optimal transport theory, and quantitative equilibrium response modeling, we develop the first comprehensive comparative statics theory for general settings. Contribution/Results: Applying this framework, we precisely identify and quantify the equilibrium effects of U.S. cognitive-skill-biased technological change on occupational sorting and income distribution. Our approach provides a unified analytical paradigm for research on multidimensional matching and technical progress.

This study addresses the inconsistency in causal effect estimates between observational studies and randomized controlled trials (RCTs) by proposing the first unified framework for decomposing causal effect heterogeneity. The framework systematically identifies and quantifies three sources of heterogeneity: differences in covariate distributions, variation in mediating pathways, and shifts in outcome-generating mechanisms. Methodologically, it formally defines effect decomposition across data types (observational vs. experimental), integrating causal inference, sensitivity analysis, and decomposition modeling, while enabling robust parameter estimation under multiple hypotheses. Evaluated through simulation studies and an empirical analysis of the “Moving to Opportunity” experiment, the framework demonstrates improved interpretability, robustness, and policy generalizability in synthesizing evidence from heterogeneous data sources.

Standard difference-in-differences (DID) methods struggle to identify counterfactual distributions under regulatory policies—such as minimum wage laws—when confronted with mass points, distributional discontinuities, nonstationarity, or unobserved selection bias. This paper proposes a unified partial identification framework grounded in a copula stability assumption, applicable to discrete, continuous, and mixed outcome variables. Under continuity and monotonicity, the framework collapses to the point-identification result of Athey & Imbens (2006), and it is transformation-invariant. Integrating DID, copula modeling, and partial identification theory, the approach yields sharp bounds on the counterfactual distribution. Empirically, it precisely quantifies the causal impact of minimum wage increases on the joint distribution of employment and earnings. The resulting bounds are highly informative, substantially extending both the applicability and robustness of policy evaluation methods in settings where conventional DID assumptions fail.

This study addresses the decomposition of wage dispersion in labor markets by explicitly accounting for worker and firm heterogeneity. It establishes a systematic and standardized framework for implementing the Abowd–Kramarz–Margolis (AKM) fixed-effects model, integrating high-dimensional panel estimation techniques with matched employer–employee microdata to deliver best practices for empirical analysis. The research delineates the methodological boundaries within which the AKM approach remains valid across diverse empirical settings and quantifies the relative contributions of worker and firm effects to overall wage inequality, thereby affirming their pivotal roles. By providing a reproducible and robust analytical toolkit, this work advances methodological rigor in labor economics and outlines promising avenues for future extensions of the framework.

This study addresses the limitations of traditional causal inference, which focuses primarily on average treatment effects and fails to capture the full distributional structure of income disparities between eastern and western Germany. The authors propose a novel counterfactual density–based causal inference framework that extends causal analysis to the entire outcome distribution. By modeling conditional densities within a Bayesian Hilbert space, the approach guarantees non-negativity and unit integral constraints. Integrating insights from the Oaxaca–Blinder decomposition, the framework identifies distinct distributional and covariate effects. Empirical application reveals multidimensional differences in wage distributions across regions, including disparities in the probability mass at zero income, offering policymakers nuanced insights beyond mean comparisons.

This study addresses the limitations of high-resolution proxies—such as nighttime lights—in capturing unobserved local economic activity after aggregation to administrative units, a constraint rooted in aggregation bias. The authors develop an inverse regression framework and introduce a triple decomposition theorem for predictive elasticity, revealing for the first time that this bias is jointly driven by administrative unit size and internal economic heterogeneity, while also clarifying the conditions under which cross-regional transferability holds. Leveraging VIIRS nighttime lights and subnational GDP or income data across Brazil, Italy, the United States, Indonesia, and Kenya, they combine elasticity decomposition, Monte Carlo simulations, and empirical validation to demonstrate that nighttime lights reliably predict economic activity only in relatively affluent regions and only after local calibration.

This study addresses the challenge in causal inference of accurately identifying treatment effects when using machine learning to predict outcome variables, compounded by the absence of effective criteria for model selection. The authors decompose prediction into three components: between-unit variation, within-unit temporal variation, and counterfactual treatment effects. They demonstrate that only the first two components are estimable from observed data and, for the first time, formally establish that the counterfactual component governs the accuracy of causal identification. To address this, they propose using within-unit temporal prediction accuracy as a structural proxy for this unobservable component, enabling model diagnostics and selection. Within a panel data framework that integrates causal theory with machine learning evaluation techniques, the proposed metric is validated on synthetic data and shown—under plausible assumptions—to yield approximately unbiased estimates of treatment effects.

In time-to-event analyses with competing risks, causal interpretation of treatment effects becomes complicated when the treatment may influence the competing event. This work proposes the first quadruple causal decomposition framework, which disentangles the total effect of treatment on the event of interest into four mutually exclusive causal pathways, explicitly characterizing the interaction between treatment and the competing event. By introducing cross-world counterfactual estimands and leveraging standard identifiability assumptions—such as exchangeability and consistency—the framework enables nonparametric identification of these effects under randomized controlled trial data. Empirical application to two real-world RCT datasets demonstrates that the proposed approach effectively clarifies the causal mechanisms underlying treatment effects in the presence of competing risks, substantially enhancing interpretability of the results.