pdcDistTSList: Permutation Distribution Distance for a List of Time Series

In Jakob-Bach/FastTSDistances: Fast dissimilarity computations for time series

Description

Simplified version of the distance used for permutation distribution clustering as described by Brandmaier (2015). Shortens the high-level code a bit and handles some errors for short time series.

Usage

pdcDistTSList(tsList, subSequenceLength = NULL)

Arguments

tsList

1) A list of numeric vectors (uni-variate time series). The dissimilarity of the list to itself (each time series to each time series) will be computed, resulting in a symmetric dissimilarity matrix. 2) A list with two components, each being a list of numeric vectors (uni-variate time series). The dissimilarity of each time series from the 1st component to each time series from the 2nd component will be computed. The entropy heuristic is only computed with the second component (for comparability to previously computed distances). 1+2) Each time series should have at least two elements.

subSequenceLength

Number of elements which form each subsequence. Will be determined as integer in [2,7] by a heuristic if not provided.

Value

The distance matrix with each entry being a numeric from the range [0,4].

References

Brandmaier, A. M. (2011). Permutation distribution clustering and structural equation model trees (Doctoral dissertation, Universität des Saarlandes, Saarbrücken).

Brandmaier, A. M. (2015). pdc: An R Package for Complexity-Based Clustering of Time Series. Journal of Statistical Software, 67(5), 1-23.

See Also

Other PDC functions: pdcDistTSListMult, pdcDistTwoTSMult, pdcDistTwoTS, pdcEntropyHeuristicMult, pdcEntropyHeuristic, pdcEntropy

Jakob-Bach/FastTSDistances documentation built on May 13, 2019, 1:15 p.m.