mlsanityData to 14 Oct 2026

Data Fusion for High-Resolution Estimation

arXiv 2508.14858 ↗First posted 20 Aug 2025stat.ME stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

High-resolution estimates of population health indicators are critical for precision public health. We propose a method for high-resolution estimation that fuses distinct data sources: an unbiased, low-resolution data source (e.g. aggregated administrative data) and a potentially biased, high-resolution data source (e.g. individual-level online survey responses). We assume that the potentially biased, high-resolution data source is generated from the population under a model of sampling bias where observables can have arbitrary impact on the probability of response but the difference in the log probabilities of response between units with the same observables is linear in the difference between sufficient statistics of their observables and outcomes. Our data fusion method learns a distribution that is closest (in the sense of KL divergence) to the online survey distribution and consistent with the aggregated administrative data and our model of sampling bias. This approach significantly reduces bias in high-resolution estimates compared to baselines that rely on a single data source alone on a testbed that includes repeated measurements of three indicators measured by both the (online) Household Pulse Survey and ground-truth data sources at two geographic resolutions over the same time period.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 69 references that are in the map. First posted on arXiv 20 Aug 2025.

Builds on

20 of 69 references.

References · 20

  1. 2018Removing Hidden Confounding by Experimental Groundingcited by 64
  2. 2018Bounds on the conditional and average treatment effect with unobserved confounding factorscited by 39
  3. 2016Covariate Balancing Propensity Score by Tailored Loss Functionscited by 34
  4. 2021Sharp Sensitivity Analysis for Inverse Propensity Weighting via Quantile Balancingcited by 32
  5. 2018Combining multiple observational data sources to estimate causal effectscited by 29
  6. 2018Flexible sensitivity analysis for observational studies without observable implicationscited by 18
  7. 2022Learning from a Biased Samplecited by 14
  8. 2021Multi-Source Causal Inference Using Control Variatescited by 13
  9. 2022Sensitivity analysis under the f-sensitivity models: a distributional robustness perspectivecited by 12
  10. 2019Efficient and robust methods for causally interpretable meta-analysis: transporting inferences from multiple randomized trials to a target populationcited by 10
  11. 2020Data fusion methods for the heterogeneity of treatment effect and confounding functioncited by 9
  12. 2023Policy Learning under Biased Sample Selectioncited by 9
8 more
  1. 2021Semiparametric sensitivity analysis: unmeasured confounding in observational studiescited by 8
  2. 2023Domain constraints improve risk prediction when outcome data is missingcited by 8
  3. 2024Distributionally Robust Policy Learning under Concept Driftscited by 6
  4. 2021Efficient Estimation Under Data Fusioncited by 4
  5. 2025Data Fusion for Partial Identification of Causal Effectscited by 3
  6. 2021Is it who you are or where you are? Accounting for compositional differences in cross-site treatment variationcited by 1
  7. 2023Data fusion using weakly aligned sourcescited by 1
  8. 2025Inferring fine-grained migration patterns across the United Statescited by 1

Built on by

Not cited yet.