distantia: Assessing Dissimilarity Between Multivariate Time Series

Provides tools to assess the dissimilarity between multivariate time-series. It is based on the psi measure described by Birks and Gordon (1985 <doi:10.1002/jqs.3390020110>), which computes dissimilarity between irregular time-series constrained by sample order. However, in this package the original idea has been extended to work with any kind of multivariate time-series, no matter whether they are regular, irregular, aligned or unaligned. Furthermore, the package allows to assess the significance of dissimilarity values by applying a restricted permutation test, allows to measure the contribution of individual variables to dissimilarity, and offers tools to transfer attributes (generally time or age, but other are possible) between sequences based on the similarity of their samples.

Package details

AuthorBlas M. Benito
MaintainerBlas M. Benito <blasbenito@gmail.com>
LicenseGPL (>= 2)
URL https://blasbenito.github.io/distantia/
Package repositoryView on CRAN
Installation Install the latest version of this package by entering the following in R:

Try the distantia package in your browser

Any scripts or data that you put into this service are public.

distantia documentation built on Oct. 30, 2019, 10:05 a.m.