Create random time series: (only works in combination with the “Generate Correlation
Matrix” option) by non-parametric testing of the correlation strenght (r) of any two nodes in
the n x n matrix against a multiple iteration derived distribution of correlation strengths
between random time series (pairwise null-model-distribution), this option allows to derive
p-values (retrieved by placing the “original” correlation value in the corresponding null-model
distribution and determining its percentile position) for each connection in
the correlation matrix that can be used for thresholding of the network (i.e. to create the
adjacency matrix) or/and for determining a threshold for subsequent association-matrix
based statistics (please refer to the “The Raw Matrix (link wise) panel”). The creation of
random time series can also be used in combination with the “Partial correlation” option
(in this case - per iteration - a “random” correlation value entering the respective pairwise
null-model distribution is controlled for the random time series of the selected nodes
in the network). Thresholding based on the non-parametric p-values is performed in the “Network Construction”
panel under “Significant/Significance level”.