EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Model‐Agnostic Influential Outlier Metric

Colin C. Jones, David A. Campbell

Stat · 2026-09 · 15 (3)

DOI: 10.1002/sta4.70163 ↗

At a glance

Journal article in Stat, published online on 2026-07-07. Written by Colin C. Jones and 1 co-authors. 31 references. The full text is freely available (open access, CC BY 4.0).

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

The influential outlier metric (IOM) provides model‐agnostic influential outlier detection. We define influence of an observation using a combination of SHapley Additive exPlanation (SHAP) values and the residual. Both are transformed using normalizing flows, changing their respective measures to Gaussian distributions. The transformed SHAP values and residuals define the IOM as a product of two independent random variables, allowing critical values for a given significance level . We illustrate the advantages and limitations of this approach in several models including the linear model, neural networks, the random forest and gradient‐boosted trees.

Cite

APA

Jones, C. C., & Campbell, D. A. (2026). Model‐Agnostic Influential Outlier Metric. Stat, 15(3). https://doi.org/10.1002/sta4.70163

Vancouver

Jones CC, Campbell DA. Model‐Agnostic Influential Outlier Metric. Stat. 2026;15(3). doi:10.1002/sta4.70163

BibTeX
@article{Jones2026,
  author = {Jones, Colin C. and Campbell, David A.},
  title = {Model‐Agnostic Influential Outlier Metric},
  journal = {Stat},
  year = {2026},
  volume = {15},
  number = {3},
  doi = {10.1002/sta4.70163}
}
Start for free →