This content refers to the previous stable release of PyMVPA. Please visit www.pymvpa.org for the most recent version of PyMVPA and its documentation.

misc.stats

Module: misc.stats

Inheritance diagram for mvpa.misc.stats:

Little statistics helper

DSMatrix

class mvpa.misc.stats.DSMatrix(data_vectors, metric='spearman')

Bases: object

DSMatrix allows for the creation of dissilimarity matrices using arbitrary distance metrics.

Initialize DSMatrix

Parameters:

• data_vectors (ndarray) – m x n collection of vectors, where m is the number of exemplars and n is the number of features per exemplar
• metric (string) – Distance metric to use (e.g., ‘euclidean’, ‘spearman’, ‘pearson’, ‘confusion’)

getFullMatrix()

getMetric()

getTriangle()

getVectorForm()

mvpa.misc.stats.chisquare(obs, exp=None)

Compute the chisquare value of a contingency table with arbitrary dimensions.

If no expected frequencies are supplied, the total N is assumed to be equally distributed across all cells.

Returns: chisquare-stats, associated p-value (upper tail)