Robust Preprocessing of Time Series Data

Methods for handling the missing values outliers are introduced in this package. The recognized missing values and outliers are replaced using a model-based approach. The model may consist of both autoregressive components and external regressors. The methods work robust and efficient, and they are fully tunable. The primary motivation for writing the package was preprocessing of the energy systems data, e.g. power plant production time series, but the package could be used with any time series data.


Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


0.3.1 by Michał Narajewski, 6 months ago

Browse source code at

Authors: Michał Narajewski [aut, cre] , Jens Kley-Holsteg [aut] , Florian Ziel [aut]

Documentation:   PDF Manual  

Task views: Time Series Analysis

MIT + file LICENSE license

Imports glmnet, MASS, Matrix, mclust, quantreg, splines, textTinyR, zoo

See at CRAN