Description: A method designed to evaluate the statistical significance of patterns in tensor data. To demonstrate the properties of TriSig, a industrial penicillin batches dataset and a metabolomics dataset from urinary samples analyzed by NMR spectroscop are used.
-
Methodology for assessing the statistical significance of patterns in tensor data.
-
Mitigation of false positive discoveries by reducing spurious patterns.
-
Handling of temporal dependencies and misalignments in three-way time series data.
-
Sensitivity to three-way data with non-identically distributed variables.
-
Corrections for multiple hypotheses under Benjamini-Hochberg procedure.
► Leonardo Alexandre, Rafael S. Costa and Rui Henriques, TriSig: Evaluating the statistical significance of triclusters, Pattern Recognition, 2023 | doi: 10.1016/j.patcog.2023.110231