The gmwm R package: a comprehensive tool for time series analysis from state-space models to robustness

TL;DR

The gmwm R package offers a comprehensive toolkit for time series analysis using wavelet variance, enabling model identification, estimation, and robustness for a wide range of models including ARMA and state-space models.

Contribution

It introduces an R package that implements wavelet variance-based inference, providing robust and efficient estimation methods for various time series models.

Findings

Enables robust estimation of time series models.

Provides a graphical summary of time series features.

Offers efficient estimation for linear state-space models.

Abstract

The gmwm R package for inference on time series models is mainly based on the quantity called wavelet variance which is derived from a wavelet decomposition of a time series. This quantity provides a means to summarize and graphically represent the features of time series in order to identify possible models. Moreover, it is used as a moment condition for model estimation through the generalized method of wavelet moments. Based on the latter method, this package not only provides an alternative method to estimate classical ARMA models but also delivers a general framework for the robust estimation of many time series models as well as a quick and efficient estimation of many linear state-space models.