arXiv subjects

Harry Aytug

Publications and source records attributed to Harry Aytug.

5 recordsLinked to original sources

arXiv2026

Attenuated Heterogeneity in Fixed-Effects Causal Forests, and a Cross-Fitted Correction

Causal forests that estimate conditional average treatment effects by averaging honest leaf-level effects across trees are widely used in fixed-effects panel settings. We show that this averaging systematically attenuates the estimated heterogeneity: the raw prediction behaves like a + b*tau(x) with slope b < 1, so the spread of the CATEs is compressed toward the average effect, and the additive recentering used to report an unbiased average treatment effect does not fix it. Benchmarking against a similarity-weight generalized random forest on the same within-transformed signal, we find both estimators attenuate but the leaf-averaging construction attenuates materially more. We characterize how b moves with the design, worsening with lower signal-to-noise, smaller panels, and higher dimension; this diagnosis is our main contribution. As a remedy we adapt the best-linear-predictor calibration of Chernozhukov et al., estimating the de-attenuation slope out-of-bag so that it is self-contained within the observational panel and asymptotically inert under a homogeneous effect. In simulations the correction cuts CATE mean-squared error by 25-42% relative to the recentering default; on a standard county minimum-wage panel the attenuation is present but mild and the correction restores the imposed spread. We ship the method in the causalfe Python package.

econ.EM↗

arXiv2026

A Fixed-Effects Causal Forest for Staggered Adoption, with an Application to Medicaid Expansion

Difference-in-differences with staggered adoption identifies group-time average treatment effects ATT(g,t) by comparing each cohort to units not yet treated, which avoids the "forbidden comparisons" that bias two-way fixed-effects estimators when effects are heterogeneous. This paper studies the covariate-conditional version of that object, tau_{g,t}(x), and estimates it with a fixed-effects causal forest. Within each (g,t) comparison block, the outcome and treatment are residualized on unit and period fixed effects inside each tree node, and honest causal trees split on treatment-effect heterogeneity in the covariates. The estimand is not new: Hatamyar, Kreif, Rocha and Huber (2023) introduced it using a doubly-robust R-learner, and Imai, Qin and Yanagi (2023) study it for a single continuous covariate. What we add is a different way to estimate it. Where those methods remove confounding by modeling nuisance functions, we remove it by differencing out unit and period effects within each tree node, following the fixed-effects residualization of Kattenberg, Scheer and Thiel (2023) and Gavrilova, Langorgen and Zoutman (2025) and carrying it into the Callaway-Sant'Anna group-time structure. In Monte Carlo experiments the estimator is the only forest-based method that stays unbiased and correctly covered for the overall effect under staggered timing with cohort-varying effects; two-way fixed effects and a pooled causal forest inherit large forbidden-comparison bias. We apply the method to the Callaway-Sant'Anna minimum-wage panel as a validation and to the staggered county-level rollout of the ACA Medicaid expansion, where it recovers an average 2.25 percentage-point fall in the uninsured rate and a conditional surface on which poorer and lower-income counties gained substantially more coverage -- heterogeneity measured along socioeconomic covariates that are not lags of the outcome.

econ.EM↗

arXiv2026

United in Currency, Divided in Growth: Dynamic Effects of Euro Adoption

Does euro adoption affect long-run economic growth? Existing evidence is mixed, reflecting limited treated countries, long horizons that challenge inference, and heterogeneity across member states. We estimate causal dynamic and heterogeneous treatment effects using Causal Forests with Fixed Effects (CFFE), a machine-learning approach that combines causal forests with two-way fixed effects. Under a conditional parallel-trends assumption, we find that euro adoption reduced annual GDP growth by 0.3-0.4 percentage points on average. Effects emerge shortly after adoption and stabilize after roughly a decade. Average effects mask substantial heterogeneity. Countries with lower initial GDP per capita experience larger and more persistent growth shortfalls than core economies. Weaker consumption and productivity growth contribute to the overall effect, while improvements in net exports partially offset these declines. A two-country New Keynesian DSGE model with hysteresis generates qualitatively similar patterns: one-size-fits-all monetary policy and scarring mechanisms produce larger output losses under monetary union than under flexible exchange rates. By jointly estimating dynamic and heterogeneous treatment effects, the analysis highlights the importance of country characteristics in assessing the long-run consequences of monetary union.

econ.EM↗

arXiv2026

To Adopt or Not to Adopt: Heterogeneous Trade Effects of the Euro

Two decades of research on the euro's trade effects have produced estimates ranging from 4% to 30%, with no consensus on the magnitude. We find evidence that this divergence may reflect genuine heterogeneity in the euro's trade effect across country pairs rather than methodological differences alone. Using Eurostat data on 15 EU countries (12 eurozone members plus Denmark, Sweden, and the UK as controls) from 1995-2015, we estimate that euro adoption increased bilateral trade by 29% on average (14.1% after fixed effects correction), but effects range from -12% to +79% across eurozone pairs. Core eurozone pairs (e.g., Germany-France, Germany-Netherlands) show large gains, while peripheral pairs involving Finland, Greece, and Portugal saw smaller or negative effects, with some negative estimates statistically significant and interpretable as trade diversion. Pre-euro trade intensity and GDP account for over 90% of feature importance in explaining this heterogeneity. Extending to EU28, we find evidence that crisis-era adopters (Slovakia, Estonia, Latvia) pull down naive estimates to 4.3%, but accounting for fixed effects recovers estimates of 13.4%, consistent with the EU15 fixed-effects baseline of 14.1%. Illustrative counterfactual analysis suggests non-eurozone members would have experienced varied effects: UK (+33%), Sweden (+22%), Denmark (+19%). The wide range of prior estimates appears to be largely a feature of the data, not a bug in the methods.

econ.EM↗

arXiv2026

causalfe: Causal Forests with Fixed Effects in Python

The causalfe package provides a Python implementation of Causal Forests with Fixed Effects (CFFE) for estimating heterogeneous treatment effects in panel data settings. Standard causal forest methods struggle with panel data because unit and time fixed effects induce spurious heterogeneity in treatment effect estimates. The CFFE approach addresses this by performing node-level residualization during tree construction, removing fixed effects within each candidate split rather than globally. This paper describes the methodology, documents the software interface, and demonstrates the package through simulation studies that validate the estimator's performance under various data generating processes.

econ.EM↗