{
  "abstract": "Model-assisted estimation uses prediction rules to improve the efficiency of estimators of finite population parameters while retaining design-based inference. Although flexible prediction methods have been considered, existing theoretical results are largely method-specific. We develop a learner-agnostic framework that replaces separate analyses for individual learners with general conditions on the sampling design and prediction error. We connect design-aware and design-agnostic cross-fitting and characterize the sampling designs under which they yield conditional independence across folds. Under suitable conditions, conditional weighting gives exact design-unbiasedness. We establish first-order equivalence to oracle estimators, leading to design consistency and asymptotic normality, and clarify when conditional and original inclusion probabilities yield the same first-order behavior. We propose consistent variance estimators based on cross-fitted residuals and construct asymptotically valid confidence intervals. Under additional model and regularity conditions, we establish asymptotic optimality through attainment of the Godambe--Joshi lower bound. Simulations show that cross-fitting substantially reduces finite-sample bias and improves variance estimation and coverage with adaptive learners.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.10904",
  "author_total": 4,
  "authors": [
    {
      "name": "Ziming An"
    },
    {
      "name": "Mehdi Dagdoug"
    },
    {
      "name": "David Haziza"
    },
    {
      "name": "Yves Tillé"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/29bq0s7q93s7z.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.10904",
  "fulltext_url": null,
  "id": "29bq0s7q93s7z",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.10904",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "math.ST"
    ],
    [
      "arxiv",
      "stat.ME"
    ],
    [
      "arxiv",
      "stat.TH"
    ],
    [
      "openalex",
      "2613|Survey Sampling and Estimation Techniques"
    ]
  ],
  "openalex": "W7212220631",
  "pdf_url": "https://arxiv.org/pdf/2609.10904",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-09",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/29bq0s7q93s7z.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:30Z",
      "native_id": "2609.10904",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.10904"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.ST",
      "subfield": "statistics"
    }
  ],
  "title": "Agnostic Model-Assisted Estimation with Machine Learning for Survey Data",
  "title_text": "Agnostic Model-Assisted Estimation with Machine Learning for Survey Data",
  "type": "preprint",
  "updated_at": "2026-10-30T12:20:36Z",
  "url": "https://research.draconitic.com/paper/29bq0s7q93s7z",
  "venue": "arXiv",
  "versions": []
}