Description
Forecasting Using Multivariate Models.
Description
Functions implementing multivariate state space models for purposes of time series analysis and forecasting. The focus of the package is on multivariate models, such as Vector Exponential Smoothing, Vector ETS (Error-Trend-Seasonal model) etc. It currently includes Vector Exponential Smoothing (VES, de Silva et al., 2010, <doi:10.1177/1471082X0901000401>), Vector ETS and simulation function for VES.
README.md
legion
The package legion implements several multivariate models for purposes of forecasting.
Here is the list of the included functions:
- ves - Vector Exponential Smoothing.
- vets - Vector ETS with PIC taxonomy.
- auto.vets - Automatic selection of restrictions for VETS.
- sim.ves - simulates data from VES.
- oves - occurrence state space vector exponential smoothing model.
Available methods:
- AIC, BIC, AICc, BICc;
- coefficients;
- fitted;
- forecast;
- actuals;
- logLik;
- modelType - type of the estimated model;
- nobs;
- nparam - number of the estimated parameters in the model;
- nvariate - number of series in the model;
- residuals - the residuals of the model (et in case of additive and log(1+et) for the multiplicative ones);
- rstandard, rstudent - standardised and studentised residuals;
- outlierdummy - extracts outliers in the model and creates dummy variables for them;
- plot - produces several plots for diagnostics purposes. See the documentation for plot.legion();
- print;
- sigma;
- simulate;
- summary;
Installation
The stable version of the package is available on CRAN, so you can install it by running:
install.packages("legion")
A recent, development version, is available via github and can be installed using "remotes" in R. First, make sure that you have remotes:
if (!require("remotes")){install.packages("remotes")}
and after that run:
remotes::install_github("config-i1/legion")