EUVIMEDEUVIMED entdecken
Crossref

Debiasing Estimates of Global Forest Cover Loss

Matthew Gordon, Eliana Stone, Megan Ayers, Luke Sanford

AEA Papers and Proceedings · 01.05.2026 · 116 · 81-86

DOI: 10.1257/pandp.20261018 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AEA Papers and Proceedings, erschienen am 01.05.2026. Verfasst von Matthew Gordon und 3 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Using machine learning predictions as proxies for difficult-to-observe outcome variables can bias empirical estimates when prediction errors correlate with treatment variables. We describe methods for detecting and correcting these biases using a sample of ground truth data. These types of data are often not available in practice, however. We construct a novel dataset on deforestation in Africa using approximately optimal sampling methods and visual interpretation of high-resolution satellite imagery. We use the data to evaluate bias in widely used satellite-derived measures of deforestation. We find that deforestation is systematically under-predicted in areas with higher rates of deforestation.

Zitieren

APA

Gordon, M., Stone, E., Ayers, M., & Sanford, L. (2026). Debiasing Estimates of Global Forest Cover Loss. AEA Papers and Proceedings, 116, 81-86. https://doi.org/10.1257/pandp.20261018

Vancouver

Gordon M, Stone E, Ayers M, Sanford L. Debiasing Estimates of Global Forest Cover Loss. AEA Papers and Proceedings. 2026;116:81-86. doi:10.1257/pandp.20261018

BibTeX
@article{Gordon2026,
  author = {Gordon, Matthew and Stone, Eliana and Ayers, Megan and Sanford, Luke},
  title = {Debiasing Estimates of Global Forest Cover Loss},
  journal = {AEA Papers and Proceedings},
  year = {2026},
  volume = {116},
  pages = {81--86},
  doi = {10.1257/pandp.20261018}
}
Kostenlos starten →