Learn R Programming

⚠️There's a newer version (8.24.0) of this package.Take me there.

forecast (version 3.18)

Forecasting functions for time series

Description

Methods and tools for displaying and analysing univariate time series forecasts including exponential smoothing via state space models and automatic ARIMA modelling.

Copy Link

Version

Install

install.packages('forecast')

Monthly Downloads

142,544

Version

3.18

License

GPL (>= 2)

Maintainer

Rob Hyndman

Last Published

February 17th, 2012

Functions in forecast (3.18)

Automatic selection of Box Cox transformation parameter

Australian monthly gas production

Fit ARIMA model to univariate time series

forecast.StructTS

Forecasting using Structural Time Series models

Log-Likelihood of an ets object

Seasonal adjustment

Forecast seasonal index

TBATS model (Exponential smoothing state space model with Box-Cox transformation, ARMA errors, Trend and Seasonal components)

Number of days in each season

BATS model (Exponential smoothing state space model with Box-Cox transformation, ARMA errors, Trend and Seasonal components)

Fit best ARIMA model to univariate time series

Moving-average smoothing

Daily morning gold prices

Interpolate missing values in a time series

Fit a fractionally differenced ARFIMA model

Forecasting time series

Forecasts for intermittent demand using Croston's method

Cross-validation statistic

One-step in-sample forecasts using ARIMA models

Random Walk Forecast

Cubic Spline Forecast

Double-Seasonal Holt-Winters Forecasting

forecast.HoltWinters

Forecasting using Holt-Winters objects

Box Cox Transformation

Exponential smoothing state space model

Multi-Seasonal Time Series

Forecasting using BATS and TBATS models

Time series display

Theta method forecast

Forecasting using stl objects

Naive forecasts

Diebold-Mariano test for predictive accuracy

Plot components from ETS model

Simulation from a time series model

(Partial) Autocorrelation Function Estimation

Exponential smoothing forecasts

Forecasting using ARIMA or ARFIMA models

Forecasting using ETS models

Accuracy measures for forecast model

Subsetting a time series

Half-hourly electricity demand

Seasonal dummy variables

Australian total wine sales

Number of differences required for a stationary series

Forecast a linear model with possible time series components

Quarterly production of woollen yarn in Australia

Fit a linear model with time series components