Data and Code for: Debiasing Estimates of Global Forest Cover Loss

Principal Investigator(s): View help for Principal Investigator(s) Matthew Gordon, Paris School of Economics; Eliana Stone, Yale University; Megan Ayers, Reed College; Luke Sanford, Yale University

Version: View help for Version V1

Name	File Type	Size	Last Modified
pp_replication_package			05/28/2026 03:54:AM

Project Citation:

Gordon, Matthew, Stone, Eliana, Ayers, Megan, and Sanford, Luke. Data and Code for: Debiasing Estimates of Global Forest Cover Loss. Nashville, TN: American Economic Association [publisher], 2026. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2026-05-29. https://doi.org/10.3886/E248240V1

Project Description

Summary: 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.

Scope of Project

Subject Terms: machine learning; deforestation; remote sensing; causal inference

JEL Classification:
      C21 Single Equation Models; Single Variables: Cross-Sectional Models; Spatial Models; Treatment Effect Models; Quantile Regressions
      C55 Large Data Sets: Modeling and Analysis
      C81 Methodology for Collecting, Estimating, and Organizing Microeconomic Data; Data Access
      Q23 Renewable Resources and Conservation: Forestry
      Q54 Climate; Natural Disasters and Their Management; Global Warming

Related Publications

Download this project

Published Versions

V1 [2026-05-29]

Export Metadata

Dublin Core

DDI 2.5

Report a Problem

Found a serious problem with the data, such as disclosure risk or copyrighted content? Let us know.

This material is distributed exactly as received from the data depositor. As of April 2026, depositors are required to submit study materials in accessible formats. ICPSR has not reviewed, checked, or processed this material. For additional information about the study, please contact the investigator(s) directly. If you have questions about the accessibility of materials distributed by ICPSR or require further assistance, please visit ICPSR's Accessibility Center.