EUVIMEDDescobrir EUVIMED
Open access · CC BY-NC-ND 4.0

Multiple multi‐sample testing under arbitrary covariance dependency

Vladimir Vutov iD, Thorsten Dickhaus iD

Statistics in Medicine · 2023

DOI: 10.1002/sim.9761 ↗

At a glance

Journal article in Statistics in Medicine, 2023. Written by Vladimir Vutov and 1 co-authors. Institution: Institute for Statistics, University of Bremen, Bremen, Germany. Major MEDLINE topics: Spectrometry, Mass, Matrix-Assisted Laser Desorption-Ionization. Cited 1 times so far (Crossref); 49 references. The full text is freely available (open access, CC BY-NC-ND 4.0). Funded by: Deutsche Forschungsgemeinschaft.

ResumoSubjectsDados bibliográficosCiteRelated studies

Abstract (original language)

Modern high‐throughput biomedical devices routinely produce data on a large scale, and the analysis of high‐dimensional datasets has become commonplace in biomedical studies. However, given thousands or tens of thousands of measured variables in these datasets, extracting meaningful features poses a challenge. In this article, we propose a procedure to evaluate the strength of the associations between a nominal (categorical) response variable and multiple features simultaneously. Specifically, we propose a framework of large‐scale multiple testing under arbitrary correlation dependency among test statistics. First, marginal multinomial regressions are performed for each feature individually. Second, we use an approach of multiple marginal models for each baseline‐category pair to establish asymptotic joint normality of the stacked vector of the marginal multinomial regression coefficients. Third, we estimate the (limiting) covariance matrix between the estimated coefficients from all marginal models. Finally, our approach approximates the realized false discovery proportion of a thresholding procedure for the marginal p ‐values for each baseline‐category logit pair. The proposed approach offers a sensible trade‐off between the expected numbers of true and false findings. Furthermore, we demonstrate a practical application of the method on hyperspectral imaging data. This dataset is obtained by a matrix‐assisted laser desorption/ionization (MALDI) instrument. MALDI demonstrates tremendous potential for clinical diagnosis, particularly for cancer research. In our application, the nominal response categories represent cancer (sub‐)types.

Subjects

MeSH terms (MEDLINE)

Spectrometry, Mass, Matrix-Assisted Laser Desorption-IonizationHumansStatistics as Topic

Author keywords

false discovery proportionhyperspectral imaging datamatrix-assisted laser desorption/ionizationmultinomial regressionmultiple marginal models

Authors and institutions

  • Institute for Statistics, University of Bremen, Bremen, Germany.

ORCID profiles: Vladimir Vutov, Thorsten Dickhaus

Funding

  • Deutsche Forschungsgemeinschaft

Cite

APA

Vutov, V., & Dickhaus, T. (2023). Multiple multi‐sample testing under arbitrary covariance dependency. Statistics in Medicine. https://doi.org/10.1002/sim.9761

Vancouver

Vutov V, Dickhaus T. Multiple multi‐sample testing under arbitrary covariance dependency. Statistics in Medicine. 2023. doi:10.1002/sim.9761

BibTeX
@article{Vutov2023,
  author = {Vutov, Vladimir and Dickhaus, Thorsten},
  title = {Multiple multi‐sample testing under arbitrary covariance dependency},
  journal = {Statistics in Medicine},
  year = {2023},
  doi = {10.1002/sim.9761}
}
Start for free →