arXiv 23 Feb 2026 · Econometrics
arXiv:2602.19703 · PDF · DOI · OpenAlex · Extracted main text
We propose a framework for testing the homogeneity of conditional average treatment effects (CATEs) across multiple experimental and observational studies. Our approach leverages multiple randomized trials to assess whether treatment effects vary with unobserved heterogeneity that differs across trials: if CATEs are homogeneous, this indicates the absence of interactions between treatment and unobservables in the mean effect. Comparing CATEs between experimental and observational data further allows evaluation of potential confounding: if the estimands coincide, there is no unobserved confounding; if they differ, deviations may arise from unobserved confounding, effect heterogeneity, or both. We extend the framework to settings with alternative identification strategies, namely instrumental variable settings and panel data with parallel trends assumptions based on differences in differences, where effects are identified only locally for subpopulations such as compliers or treated units. In these contexts, testing homogeneity is useful for assessing whether local effects can be extrapolated to the total population. We suggest a test based on double machine learning that accommodates high-dimensional covariates in a data-driven way and investigate its finite-sample performance through a simulation study. Finally, we apply the test to the International Stroke Trial (IST), a large multi-country randomized controlled trial in patients with acute ischaemic stroke that evaluated whether early treatment with aspirin altered subsequent clinical outcomes. Our methodology provides a flexible tool for both validating identification assumptions and understanding the generalizability of estimated treatment effects.
appendix boundary found by appendix_titled_section at “Appendix ” · 84% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Nicolas Apfel and Julia Hatamyar and Martin Huber and Jannis Kueck (2024) Learning control variables and instruments for causal analysis in observational data self | 1.000 | 9 | 5 | 100% |
| 2 | Yang, Shu and Gao, Chenyin and Zeng, Donglin and Wang, Xiaofei (2023) Elastic integrative analysis of randomised trial and real-world data for treatment heterogeneity estimation | 0.811 | 4 | 2 | 100% |
| 3 | Lelova, Konstantina and Cooper, Gregory F and Triantafillou, Sofia (2025) Testing Identifiability and Transportability with Observational and Experimental Data | 0.737 | 3 | 2 | 100% |
| 4 | Liu, Muye and Xie, Jun (2025) When Is Causal Inference Possible? A Statistical Test for Unmeasured Confounding | 0.737 | 3 | 2 | 100% |
| 5 | Parikh, Harsh and others (2025) A Double Machine Learning Approach for Combining Experimental and Observational Studies | 0.737 | 3 | 2 | 100% |
| 6 | Triantafillou, Sofia and Jabbari, Fattaneh and Cooper, Gregory F (2023) Learning treatment effects from observational and experimental data | 0.737 | 3 | 2 | 100% |
| 7 | Wu, Lili and Yang, Shu (2022) Integrative $ R $-learner of heterogeneous treatment effects combining experimental and observational studies | 0.737 | 3 | 2 | 100% |
| 8 | Yang, Shu and Zeng, Donglin and Wang, Xiaofei (2020) Improved inference for heterogeneous treatment effects using real-world data subject to hidden confounding | 0.737 | 3 | 2 | 100% |
| 9 | J Angrist and I Fernández-Val (2010) Extrapolate-ing: External validity and overidentification in the late framework | 0.644 | 2 | 2 | 100% |
| 10 | J. Angrist and G. Imbens and D. Rubin Identification of Causal Effects using Instrumental Variables | 0.644 | 2 | 2 | 100% |
Showing the top 10 of 49 scored citations.