The stippled grid points are statistically significant: (mis)uses of false discovery rate correction for geospatial data

Peer-reviewed articles in the geosciences routinely assess statistical significance in spatially distributed data. Statistical significance is often assessed independently at each grid point, while formal adjustment for multiple testing is applied less consistently. Although several approaches to account for multiple testing exist, their application to geosciences data is not always straightforward, as these data often exhibit spatially coherent signals. In this work we revisit the Benjamini-Hochberg (BH) false discovery rate (FDR) correction, which is a commonly used method to account for multiple testing, in the context of spatially structured datasets. We first highlight how neglecting multiple-testing correction can substantially inflate the number of false positives. We further show that the BH correction approach proposed in literature for application in geosciences can yield counterintuitive results when applied to spatially coherent signals that cover large fractions of a spatial domain. To illustrate the latter point, we provide an example based on near-surface air temperature composites following sudden stratospheric warmings. We show that when anomalies are spatially coherent, restricting the spatial domain can increase the BH-corrected significance threshold. Consequently, the same underlying field can display a larger number of statistically significant grid points solely due to domain selection, despite unchanged data. We explain this behavior from the point of view of the rank-based structure of the BH correction and discuss its implications for spatial inference and uncertainty quantification in the geosciences. Furthermore, a numerical experiment confirms that the larger the fraction of true positives the higher the BH-corrected significance threshold becomes for a set FDR level. Building on these insights, we outline practical recommendations for transparent and robust significance assessment in geoscientific applications. These include clearly documenting multiple-testing corrections when adjusted pointwise significance is shown, cautious interpretation of adjusted thresholds, careful avoidance of a posteriori domain selection and considering spatially aware alternatives such as regional or cluster-based inference when appropriate. Overall, our results highlight both the need to account for multiple-testing, and potential issues with a naïve application and interpretation of the BH correction. We hope that our work may contribute to more robust statistical testing in the geosciences.

Authors

Institutions

Publication Details

Journal
Geoscientific model development
Published
2026-11-17
DOI
https://doi.org/10.5194/gmd-19-10917-2026
Primary Topic
Spatial and Panel Data Analysis
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

The stippled grid points are statistically significant: (mis)uses of false discovery rate correction for geospatial data

Leonardo Olivetti, Michael Schütte, Gabriele Messori, Flavio Pons
2 links
Geoscientific model development
Spatial and Panel Data Analysis
article

The stippled grid points are statistically significant: (mis)uses of false discovery rate correction for geospatial data

Leonardo Olivetti, Michael Schütte, Gabriele Messori, Flavio Pons
article en

Abstract

Peer-reviewed articles in the geosciences routinely assess statistical significance in spatially distributed data. Statistical significance is often assessed independently at each grid point, while formal adjustment for multiple testing is applied less consistently. Although several approaches to account for multiple testing exist, their application to geosciences data is not always straightforward, as these data often exhibit spatially coherent signals. In this work we revisit the Benjamini-Hochberg (BH) false discovery rate (FDR) correction, which is a commonly used method to account for multiple testing, in the context of spatially structured datasets. We first highlight how neglecting multiple-testing correction can substantially inflate the number of false positives. We further show that the BH correction approach proposed in literature for application in geosciences can yield counterintuitive results when applied to spatially coherent signals that cover large fractions of a spatial domain. To illustrate the latter point, we provide an example based on near-surface air temperature composites following sudden stratospheric warmings. We show that when anomalies are spatially coherent, restricting the spatial domain can increase the BH-corrected significance threshold. Consequently, the same underlying field can display a larger number of statistically significant grid points solely due to domain selection, despite unchanged data. We explain this behavior from the point of view of the rank-based structure of the BH correction and discuss its implications for spatial inference and uncertainty quantification in the geosciences. Furthermore, a numerical experiment confirms that the larger the fraction of true positives the higher the BH-corrected significance threshold becomes for a set FDR level. Building on these insights, we outline practical recommendations for transparent and robust significance assessment in geoscientific applications. These include clearly documenting multiple-testing corrections when adjusted pointwise significance is shown, cautious interpretation of adjusted thresholds, careful avoidance of a posteriori domain selection and considering spatially aware alternatives such as regional or cluster-based inference when appropriate. Overall, our results highlight both the need to account for multiple-testing, and potential issues with a naïve application and interpretation of the BH correction. We hope that our work may contribute to more robust statistical testing in the geosciences.

Geoscientific model developmentVol. 19(22)
Uppsala University (SE), Centre National de la Recherche Scientifique (FR), Stockholm University (SE), Université de Versailles Saint-Quentin-en-Yvelines (FR), Commissariat à l'Énergie Atomique et aux Énergies Alternatives (FR), Université Paris-Saclay (FR), CEA Paris-Saclay - Etablissement de Saclay (FR), Laboratoire des Sciences du Climat et de l'Environnement (FR)
European Commission, Svenska Forskningsrådet Formas, Vetenskapsrådet, Horizon 2020 Framework Programme, HORIZON EUROPE Framework Programme
Spatial and Panel Data Analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon