Characterizing multivariate decoding models based on correlated EEG spectral features

ObjectiveMultivariate decoding methods are popular techniques for analysis of neurophysiological data. The present study explored potential interpretative problems with these techniques when predictors are correlated.MethodsData from sensorimotor rhythm-based cursor control experiments was analyzed offline with linear univariate and multivariate models. Features were derived from autoregressive (AR) spectral analysis of varying model order which produced predictors that varied in their degree of correlation (i.e., multicollinearity).ResultsThe use of multivariate regression models resulted in much better prediction of target position as compared to univariate regression models. However, with lower order AR features interpretation of the spectral patterns of the weights was difficult. This is likely to be due to the high degree of multicollinearity present with lower order AR features.ConclusionsCare should be exercised when interpreting the pattern of weights of multivariate models with correlated predictors. Comparison with univariate statistics is advisable.SignificanceWhile multivariate decoding algorithms are very useful for prediction their utility for interpretation may be limited when predictors are correlated.

► Decoding algorithms are effective for classifying EEG data. ► Decoding algorithm weights may be difficult to interpret. ► Simple univariate analyses should accompany complex statistical models.