Non-parametric statistical analysis is becoming more common in single trial EEG and ERP analysis. The advantage of non-parametric statistics is that it does not depend on assumptions as parametric tests, and still the results can be as powerful as parametric tests when the assumptions are met.
In CURRY, non-parametric statistics using topographical ANOVA randomization methods is available for both individual subjects as well as for group studies. Whether you are interested in seeing a statistical effect for a group of subjects or want to test if a certain ERP component is significant in a single subject, CURRY displays these results in a comprehensive way. The statistical results can be exported immediately for further processing or publication.
A detailed description of the method and its capabilities is described in the following papers:
- Kognitive Neurophysiologie 2014 7 1 – Wagner et al; Non-Parametric Statistical Analysis of EEG/MEG Map Topographies and Source Distributions on the Epoch Level.
-
Biomed. Eng. Lett. 2017 – Wagner et al; Statistical non-parametric mapping in sensor space.
CURRY
The non-parametric statistical analysis module is part of the following CURRY packages: