CRAN
TSPred 4.0
Functions for Benchmarking Time Series Prediction
Released Jun 21, 2018 by Rebecca Pontes Salles
This package cannot yet be used with Renjin it depends on other packages which are not available: MuMIn 1.42.1
An older version of this package is
more compatible with Renjin.
Dependencies
MuMIn 1.42.1 EMD 1.5.7 wavelets 0.3-0 forecast 8.4 vars 1.5-3 KFAS 1.3.2
Functions for time series preprocessing, decomposition, prediction and accuracy assessment using automatic linear modelling. The generated linear models and its yielded prediction errors can be used for benchmarking other time series prediction methods and for creating a demand for the refinement of such methods. For this purpose, benchmark data from prediction competitions may be used.