Quinn Lanners, Cynthia Rudin, Alexander Volfovsky, Harsh Parikh
arXiv 30 May 2025 · Statistics — Methodology
arXiv:2505.24296 · PDF · DOI · OpenAlex · Extracted main text
Data fusion techniques integrate information from heterogeneous data sources to improve learning, generalization, and decision making across data sciences. In causal inference, these methods leverage rich observational data to improve causal effect estimation, while maintaining the trustworthiness of randomized controlled trials. Existing approaches often relax the strong no unobserved confounding assumption by instead assuming exchangeability of counterfactual outcomes across data sources. However, when both assumptions simultaneously fail - a common scenario in practice - current methods cannot identify or estimate causal effects. We address this limitation by proposing a novel partial identification framework that enables researchers to answer key questions such as: Is the causal effect positive or negative? and How severe must assumption violations be to overturn this conclusion? Our approach introduces interpretable sensitivity parameters that quantify assumption violations and derives corresponding causal effect bounds. We develop doubly robust estimators for these bounds and operationalize breakdown frontier analysis to understand how causal conclusions change as assumption violations increase. We apply our framework to the Project STAR study, which investigates the effect of classroom size on students' third-grade standardized test performance. Our analysis reveals that the Project STAR results are robust to simultaneous violations of key assumptions, both on average and across various subgroups of interest. This strengthens confidence in the study's conclusions despite potential unmeasured biases in the data.
appendix boundary found by appendix_command · 30% 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 | Parikh, H., Morucci, M., Orlandi, V., Roy, S., Rudin, C., and Volfov… (2023) A double machine learning approach to combining experimental and observational data self | 0.894 | 7 | 5 | 71% |
| 2 | Mosteller, F (1995) The tennessee study of class size in the early school grades | 0.843 | 3 | 3 | 100% |
| 3 | Achilles, C., Bain, H. P., Bellott, F., Boyd-Zaharias, J., Finn, J.,… (2008) Tennessee's Student Teacher Achievement Ratio (STAR) project | 0.843 | 3 | 3 | 100% |
| 4 | Yang, S., Gao, C., Zeng, D., and Wang, X (2023) Elastic integrative analysis of randomised trial and real-world data for treatment heterogeneity estimation | 0.830 | 7 | 3 | 57% |
| 5 | Chernozhukov, V., Chetverikov, D., Demirer, M., Duflo, E., Hansen, C… (2018) Double/debiased machine learning for treatment and structural parameters | 0.811 | 5 | 2 | 80% |
| 6 | Lin, X., Tarp, J. M., and Evans, R. J (2025) Combining experimental and observational data through a power likelihood | 0.794 | 6 | 3 | 50% |
| 7 | Brantner, C. L., Chang, T.-H., Nguyen, T. Q., Hong, H., Di Stefano,… (2023) Methods for integrating trials and non-experimental data to examine treatment effect heterogeneity | 0.737 | 5 | 3 | 40% |
| 8 | Kallus, N., Puli, A. M., and Shalit, U (2018) Removing hidden confounding by experimental grounding | 0.737 | 5 | 3 | 40% |
| 9 | Rosenman, E. T., Basse, G., Owen, A. B., and Baiocchi, M (2023) Combining observational and experimental datasets using shrinkage estimators | 0.737 | 5 | 3 | 40% |
| 10 | Degtiar, I. and Rose, S (2023) A review of generalizability and transportability | 0.737 | 4 | 3 | 50% |
Showing the top 10 of 74 scored citations.
arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.
| Citing paper | Intensity | Mentions | Sections | |
|---|---|---|---|---|
| 1 | Partial identification via conditional linear programs: estimation and policy learning | 0.405 | 1 | 1 |
| 2 | Partial Identification of Causal Effects that Vary by Setting | 0.405 | 1 | 1 |