PreprintarXiv licencearXiv
Unidentified prediction-risk rankings under spatial sampling with fixed inclusion probabilities
Abstract
For Gaussian spatial prediction, we construct positive sampling mechanisms with identical observation laws and conditional site inclusion probabilities, yet opposite risk rankings for two fixed predictors. The construction selects two of four sites and allows independent Gaussian measurement error.
Related
- Low-Order Inclusion Probabilities Do Not Determine Asymptotic Normality
- Opening Rankings from Engine Self-Play Are Less Certain Than They Look: Sampling Error, Draws, and Strength Dependence in Strength-Limited Stockfish Games
- Improving Minority Population Sampling with BISG Probabilities: Evidence from a Survey of Jewish Americans
- Gradient boosting machine for survival prediction in studies with general failure-time outcome-dependent sampling design.
- Edge-Defect Spectral Methods for Higher-Order Rankings of Spanning Tree Counts
BibTeX
@misc{shirota2026unidentified,
title = {{Unidentified prediction-risk rankings under spatial sampling with fixed inclusion probabilities}},
author = {Shinichiro Shirota},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.41726},
eprint = {2610.41726},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.41726},
}
RIS
TY - UNPB
TI - Unidentified prediction-risk rankings under spatial sampling with fixed inclusion probabilities
AU - Shinichiro Shirota
PY - 2026
DA - 2026/10/30
PB - arXiv
DO - 10.48550/arxiv.2610.41726
UR - https://arxiv.org/abs/2610.41726
AB - For Gaussian spatial prediction, we construct positive sampling mechanisms with identical observation laws and conditional site inclusion probabilities, yet opposite risk rankings for two fixed predictors. The construction selects two of four sites and allows independent Gaussian measurement error.
ER -