smooth

What R package do you use when you want to produce forecasts for a time series? The answer would probably be [crayon-5ed6466b04656079482297-i/]. While this is a very good package, that contains a lot of useful functions, some of them are rather restrictive. [crayon-5ed6466b04661089053374-i/] package for R contains several more flexible functions for forecasting purposes. The list of functions includes: [crayon-5ed6466b04664389668473-i/] - the function that implements ETS (exponential smoothing in Error-Trend-Seasonal taxonomy) model. The advantages of the function in comparison with [crayon-5ed6466b04666493928224-i/] function from [crayon-5ed6466b04668135932111-i/] package are discussed here; [crayon-5ed6466b0466a458329383-i/] - state-space ARIMA model, the function that implements versatile and flexible ARIMA that allows estimating simple and seasonal ARIMA using advanced methods; [crayon-5ed6466b0466c595257525-i/] - Multiple Seasonal ARIMA, that allows constructing models with several seasonalities (e.g. for high frequency data) in a reasonable time; [crayon-5ed6466b0466d069996343-i/] - Complex Exponential Smoothing, model that side steps the ETS taxonomy and allows producing non-linear forecasting trajectories; [crayon-5ed6466b0466f419573522-i/] - Generalised Univariate Model - model that underlies them all; [crayon-5ed6466b04671314169858-i/] and [crayon-5ed6466b04674492870242-i/] -...
Read More

greybox

[crayon-5ed6466b051eb782816784-i/] is a toolbox of functions for modelling and forecasting purposes. The main focus of the package on the regression models and the instruments for models diagnostics and forecasts evaluation. At the moment the package includes the following functions: [crayon-5ed6466b051f2791562291-i/] - Advanced Linear Model that implements likelihood estimation of parameters for Normal, Laplace, Logistic, S, Folded Normal, Log Normal, Chi-Squared, Poisson, Negative Binomial, Cumulative Logistic and Cumulative Normal distributions. In a sense this is similar to [crayon-5ed6466b051f5123797458-i/], but with a different set of distributions and with a focus on forecasting. [crayon-5ed6466b051f7013253388-i/] - Function produces lags and leads of the provided data. [crayon-5ed6466b051f9157833038-i/] - Function implements stepwise AIC based on partial correlations. [crayon-5ed6466b051fb134761229-i/] - Function combines the regression models from the provided data based on IC weigths and returns the combined [crayon-5ed6466b051fd208229714-i/] object. [crayon-5ed6466b051ff183789747-i/] - rolling origin evaluation (see the vignette). [crayon-5ed6466b05201360008414-i/] - Regression for Multiple Comparison of forecasting methods. Can be used, for example, when RelMAE is calculated for several forecasting methods and an analysis of statistical...
Read More