MétaCan
Menu
Back to cohort
Record W4417212914 · doi:10.1016/j.spasta.2025.100948

A heavy-tailed model for multivariate spatial processes

2025· article· en· W4417212914 on OpenAlex
Paritosh K. Roy, Alexandra M. Schmidt

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueSpatial Statistics · 2025
Typearticle
Languageen
FieldEconomics, Econometrics and Finance
TopicSpatial and Panel Data Analysis
Canadian institutionsMcGill UniversityMcGill University Health Centre
FundersFonds de recherche du Québec – Nature et technologiesAlliance de recherche numérique du CanadaNatural Sciences and Engineering Research Council of CanadaMcGill University
KeywordsMultivariate statisticsMultivariate analysisCovariateVariance (accounting)Multivariate normal distribution

Abstract

fetched live from OpenAlex

Environmental data commonly involves measuring multiple pollutants, such as NO 2 and PM 10 levels, at some fixed sites across a region. Data analysts aim to describe the processes accounting for covariance across space and among pollutants, usually assuming a multivariate spatial Gaussian model with a stationary covariance function. However, the observed data distribution often exhibits heterogeneous variability, resulting in heavier tails than the Gaussian distribution. To address these challenges by avoiding data transformation, we propose a flexible multivariate spatial model with spatially varying covariate-dependent variance that naturally accommodates heavy-tailed distributions. Specifically, we extend the linear model of coregionalization by modeling the variances of the processes, allowing them to vary across space and depending on covariates. We discuss the properties of the proposed model and outline a Bayesian inference procedure implemented using the software Stan . As the model involves several Gaussian process components, we further discuss Vecchia-based approximation methods for analyzing large spatial datasets. Artificial data analyses suggest that the model’s parameters are identifiable and can accurately detect outlying observations if they exist, underscoring the model’s reliability and robustness. The model quantifies uncertainty and captures local structures more effectively than the multivariate Gaussian model when applied to maximum concentrations of NO 2 and PM 10 on a day at 382 sites across Italy. Further, the described approximation methods show effectiveness in analyzing large spatial datasets.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.945
Threshold uncertainty score0.992

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.044
GPT teacher head0.270
Teacher spread0.227 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it