Summary statistics

As in univariate and multivariate analysis, in FDA summary statistics can be used to summarize a set of functional observations.

Location

The following statistics are available in scikit-fda in order to obtain a measure of the location or central tendency of functional data.

skfda.exploratory.stats.mean(X[, weights])	Compute the mean of all the samples in a FData object.
skfda.exploratory.stats.gmean(X)	Compute the geometric mean of all the samples in a FDataGrid object.
skfda.exploratory.stats.trim_mean(X, ...[, ...])	Compute the trimmed means based on a depth measure.
skfda.exploratory.stats.depth_based_median(X)	Compute the median based on a depth measure.
skfda.exploratory.stats.geometric_median(X, *)	Compute the geometric median.
skfda.exploratory.stats.fisher_rao_karcher_mean(...)	Compute the Karcher mean under the elastic metric.

Dispersion

For obtaining a measure of the dispersion of the data, the following statistics can be used.

skfda.exploratory.stats.cov(X[, correction])	Compute the covariance.
skfda.exploratory.stats.var(X[, correction])	Compute the variance of a set of samples in a FData object.
skfda.exploratory.stats.std()	Compute the standard deviation of all the samples in a FData object.