{
  "slug": "leveraging-predictive-modelling-from-multiple-sources-of-big-data-to-improve-sample-efficiency-and-reduce-survey-nonresponse-error",
  "title": "Leveraging Predictive Modelling from Multiple Sources of Big Data to Improve Sample Efficiency and Reduce Survey Nonresponse Error",
  "authors": "with David Dutwin, Patrick Coyle, Ipek Bilgen, and Ned English",
  "venue": "Journal of Survey Statistics and Methodology",
  "year": 2023,
  "category": "survey",
  "section": "peerReviewed",
  "status": "published",
  "visibility": "public-pdf",
  "doi": "10.1093/jssam/smad016",
  "canonical_url": "https://doi.org/10.1093/jssam/smad016",
  "summary": "The question in this paper is whether big-data classifiers can improve sample targeting for hard-to-reach and low-incidence survey populations. Using 15 classifiers trained on a large probability-based panel and tested across three survey datasets, the analysis shows that the models generally outperform geographic clustering and often improve on vendor flags, usually by trading some coverage for noticeably higher incidence. Those gains vary across targets, making classifier-based sampling most useful when researchers care about efficiently finding specific subpopulations.",
  "metadata_url": "https://jyl19.github.io/papers/leveraging-predictive-modelling-from-multiple-sources-of-big-data-to-improve-sample-efficiency-and-reduce-survey-nonresponse-error/metadata.json",
  "summary_url": "https://jyl19.github.io/papers/leveraging-predictive-modelling-from-multiple-sources-of-big-data-to-improve-sample-efficiency-and-reduce-survey-nonresponse-error/summary.md",
  "pdf_url": "https://jyl19.github.io/papers/leveraging-predictive-modelling-from-multiple-sources-of-big-data-to-improve-sample-efficiency-and-reduce-survey-nonresponse-error/paper.pdf"
}