In:
Brain Sciences, MDPI AG, Vol. 9, No. 8 ( 2019-08-20), p. 208-
Abstract:
A foundation of medical research is time series analysis—the behavior of variables of interest with respect to time. Time series data are often analyzed using the mean, with statistical tests applied to mean differences, and has the assumption that data are stationary. Although widely practiced, this method has limitations. Here we present an alternative statistical approach with sample analysis that provides a summary statistic accounting for the non-stationary nature of time series data. This work discusses the use of entropy as a measurement of the complexity of time series, in the context of Neuroscience, due to the non-stationary characteristic of the data. To elucidate our argument, we conducted entropy analysis on a sample of electroencephalographic (EEG) data from an interventional study using non-invasive electrical brain stimulation. We demonstrated that entropy analysis could identify intervention-related change in EEG data, supporting that entropy can be a useful “summary” statistic in non-linear dynamical systems.
Type of Medium:
Online Resource
ISSN:
2076-3425
DOI:
10.3390/brainsci9080208
Language:
English
Publisher:
MDPI AG
Publication Date:
2019
detail.hit.zdb_id:
2651993-8
