Litcius/Paper detail

On the stability of canonical correlation analysis and partial least squares with application to brain-behavior associations

Markus Helmer, Shaun Warrington, Ali‐Reza Mohammadi‐Nejad, Jie Lisa Ji, Amber Howell, Benjamin Rosand, Alan Anticevic, Stamatios N. Sotiropoulos, John D. Murray

2024Communications Biology93 citationsDOIOpen Access PDF

Abstract

Associations between datasets can be discovered through multivariate methods like Canonical Correlation Analysis (CCA) or Partial Least Squares (PLS). A requisite property for interpretability and generalizability of CCA/PLS associations is stability of their feature patterns. However, stability of CCA/PLS in high-dimensional datasets is questionable, as found in empirical characterizations. To study these issues systematically, we developed a generative modeling framework to simulate synthetic datasets. We found that when sample size is relatively small, but comparable to typical studies, CCA/PLS associations are highly unstable and inaccurate; both in their magnitude and importantly in the feature pattern underlying the association. We confirmed these trends across two neuroimaging modalities and in independent datasets with n ≈ 1000 and n = 20,000, and found that only the latter comprised sufficient observations for stable mappings between imaging-derived and behavioral features. We further developed a power calculator to provide sample sizes required for stability and reliability of multivariate analyses. Collectively, we characterize how to limit detrimental effects of overfitting on CCA/PLS stability, and provide recommendations for future studies.

Topics & Concepts

InterpretabilityCanonical correlationOverfittingPartial least squares regressionGeneralizability theoryMultivariate statisticsStability (learning theory)CorrelationArtificial intelligencePattern recognition (psychology)Partial correlationComputer scienceDiscriminative modelStatisticsData miningMathematicsMachine learningArtificial neural networkGeometryFunctional Brain Connectivity StudiesNeural dynamics and brain functionAdvanced Neuroimaging Techniques and Applications