On the Statistical Normality Rate of EEG Ambient Signal of Healthy Subjects and Its Dependence on Data-Observation Duration

Abstract

Determination of whether or not the electroencephalography (EEG) ambient signal is Gaussian-distributed is important for a variety of engineering applications, such as cognitive studies and cortical source localization, as well as for a theoretical understanding of the brain’s physiology. The statistical normality of EEG ambient signals has variably been affirmed/negated in the research literature. Therefore, in light of the evolving applications of EEG, one prime objective of this work is to statistically characterize the baseline EEG signal obtained from healthy subjects to be used as a reference in future studies that involve EEG signals. In addition, this present work will critically examine the alleged normality trend by introducing more appropriately rigorous statistical techniques to reveal/characterize the statistical normality of EEG datasets. Then, this work will apply these statistical tools quantitatively to a dataset collected from healthy subjects using high-density EEG recordings with over an order-of-magnitude more electrodes compared to previously reported works. The analysis results show that the maximal data-observation duration is found to be at most 0.2 seconds for a normality-test positivity rate of 98%; for 95%, 90%, 85%, and 80%, the respective ceilings can relax, respectively, to 0.3, 1.0, 1.6, and 2.9 seconds.