Optimising analysis choices for multivariate decoding: creating pseudotrials using trial averaging and resampling

Abstract

AbstractMultivariate pattern analysis (MVPA) is a popular technique that can distinguish between condition-specific patterns of activation. Applied to neuroimaging data, MVPA decoding for inference uses above chance decoding to identify statistically reliable condition-specific information in neuroimaging data which may be missed by univariate methods. However, several analysis choices influence decoding success, and the combined effects of these choices have not been fully evaluated. We systematically assessed the influence of trial averaging and resampling on decoding accuracy and subsequent statistical outcome on simulated data. Although the optimal parameters varied with the classifier and cross-validation approach used, we found that modest trial averaging using roughly 5-10% of the total number of trials per condition improved accuracy and associated t-statistics. In addition, a resampling value of 2 could improve t-statistics and classification performance, but was not always necessary. We provide code to allow researchers to optimise analyses for the parameters of their data.