.png){kind=icon}
Return
Regression coefficient estimation from remote sensing maps
.png){kind=icon}
PRE
AI
DOI：10.1016/j.rse.2025.114949.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Regression coefficient estimation from maps alone may result in biased conclusions. • Prediction-powered inference (PPI) uses ground truth data to correct for map bias. • PPI coefficient estimates also have lower uncertainty than using ground truth alone. • We apply PPI to regression use cases with map error in covariates, outcome, or both. • We simulate adding noise and bias to maps and observe their effects on PPI estimates.
Keywords:
regression coefficient estimation
prediction-powered inference
map bias
uncertainty reduction
simulation study
Journal
IF:
11.4
Papers:
1.1W
Citations:
9.4W
Organization
Cited Papers
Global maps of cropland extent and change show accelerated cropland expansion in the twenty-first century.png)
NATURE FOOD
OAAI
NATURE FOODIF21.9
OAAIShareSaveShareSaveShareSave
ShareSaveShareSaveShareSave
View more