Statistics#
Functions for statistical analysis.
Parametric statistics (see scipy.stats
and statsmodels
for more
options):
|
Perform one-sample t-test. |
|
Independent samples t-test without p calculation. |
|
Perform a 1-way ANOVA. |
|
Compute M-way repeated measures ANOVA for fully balanced designs. |
|
Compute F-value thresholds for a two-way ANOVA. |
|
Fit Ordinary Least Squares (OLS) regression. |
|
Estimate regression-based evoked potentials/fields by linear modeling. |
Mass-univariate multiple comparison correction:
|
P-value correction with Bonferroni method. |
|
P-value correction with False Discovery Rate (FDR). |
Non-parametric (clustering) resampling methods:
|
Create a sparse binary adjacency/neighbors matrix. |
|
Cluster-level statistical permutation test. |
|
Non-parametric cluster-level paired t-test. |
|
One sample/paired sample permutation test based on a t-statistic. |
|
Non-parametric cluster-level test for spatio-temporal data. |
|
Non-parametric cluster-level paired t-test for spatio-temporal data. |
|
Assemble summary SourceEstimate from spatiotemporal cluster results. |
|
Get confidence intervals from non-parametric bootstrap. |
Compute adjacency
matrices for cluster-level statistics:
|
Find the adjacency matrix for the given channels. |
|
Parse FieldTrip neighbors |
|
Compute adjacency from distances in a source space. |
|
Compute adjacency for a source space activation. |
|
Compute adjacency from triangles. |
|
Get vertices on each hemisphere that are close to the other hemisphere. |
|
Compute adjacency for a source space activation over time. |
|
Compute adjacency from triangles and time instants. |
|
Compute adjacency from distances in a source space and time instants. |