forecast.gts: Forecast a hierarchical or grouped time series
In VaughanR0/Streamline-R: Hierarchical and Grouped Time Series

Description Usage Arguments Details Value Author(s) References See Also Examples

Methods for forecasting hierarchical or grouped time series.

## S3 method for class 'gts'
forecast(object,
		h = ifelse(frequency(object$bts) > 1L, 2L * frequency(object$bts), 10L), 
		method = c("comb", "bu", "mo", "tdgsa", "tdgsf", "tdfp"),
		weights = c("wls", "ols", "mint", "nseries"),
		fmethod = c("ets", "arima", "rw"), 
		algorithms = c("lu", "cg", "chol", "recursive", "slm"),
		covariance = c("shr", "sam"),
		keep.fitted = FALSE, keep.resid = FALSE,
		keep.model = FALSE, keep.intervals = FALSE,
		do.season = FALSE, allow.negative = FALSE,
		positive = FALSE, lambda = NULL, level, 
		parallel = FALSE, num.cores = 2, FUN = NULL,
		xreg = NULL, newxreg = NULL, ...)

`object`	Hierarchical or grouped time series object of class `{gts}`
`h`	Forecast horizon
`method`	Method for distributing forecasts within the hierarchy. See details
`weights`	Weights used for "optimal combination" method: `weights="ols"` uses an unweighted combination (as described in Hyndman et al 2011); `weights="wls"` uses weights based on forecast variances (as described in Hyndman et al 2015); `weights="mint"` uses a full covariance estimate to determine the weights (as described in Hyndman et al 2016); `weights="nseries"` uses weights based on the number of series aggregated at each node.
`fmethod`	Forecasting method to use
`algorithms`	An algorithm to be used for computing the combination forecasts (i.e. when `method=="comb"`). The combination forecasts are based on an ill-conditioned regression model. "lu" indicates LU decomposition is used; "cg" indicates a conjugate gradient method; "chol" corresponds to a Cholesky decomposition; "recursive" indicates the recursive hierarchical algorithm of Hyndman et al (2015); "slm" uses sparse linear regression. Note that `algorithms = "recursive"` and `algorithms = "slm"` cannot be used if `weights="mint"`.
`covariance`	Type of the covariance matrix to be used with `weights="mint"`: either a shrinkage estimator (`"shr"`) with shrinkage towards the diagonal; or a sample covariance matrix (`"sam"`).
`keep.fitted`	If TRUE, keep fitted values at all levels.
`keep.resid`	If TRUE, keep residuals at all levels.
`keep.model`	If TRUE, keep model descriptions at all levels.
`keep.intervals`	If TRUE, keep prediction intervals at all levels.
`do.season`	If TRUE, allow seasonal models at the lower levels if even the top level is not seasonal.
`allow.negative`	If TRUE, forecasts are not truncated to 0 when negative use this as setting `lambda=0` requires all bts to be strictly positive and in my experience this is not reliable anyway - probably due to re-allocation between levels.
`positive`	If TRUE, forecasts are forced to be strictly positive
`lambda`	Box-Cox transformation parameter
`level`	Level used for "middle-out" method (only used when `method="mo"`)
`parallel`	If TRUE, import `parallel` package to allow parallel processing
`num.cores`	If parallel = TRUE, specify how many cores are going to be used
`FUN`	A user-defined function that returns an object which can be passed to the `forecast` function. It is applied to all series in order to generate base forecasts. When `FUN` is not `NULL`, `fmethod`, `positive` and `lambda` are all ignored. Suitable values for `FUN` are `tbats` and `stlf`.
`xreg`	When `fmethod = "arima"`, a vector or matrix of external regressors used for modelling, which must have the same number of rows as the original univariate time series
`newxreg`	When `fmethod = "arima"`, a vector or matrix of external regressors used for forecasting, which must have the same number of rows as the `h` forecast horizon
`...`	Other arguments passed to `ets`, `auto.arima` or `FUN`.

Base methods implemented include ETS, ARIMA and the naive (random walk) models. Forecasts are distributed in the hierarchy using bottom-up, top-down, middle-out and optimal combination methods.

Three top-down methods are available: the two Gross-Sohl methods and the forecast-proportion approach of Hyndman, Ahmed, and Athanasopoulos (2011). The "middle-out" method "mo" uses bottom-up ("bu") for levels higher than level and top-down forecast proportions ("tdfp") for levels lower than level.

For non-hierarchical grouped data, only bottom-up and combination methods are possible, as any method involving top-down disaggregation requires a hierarchical ordering of groups.

When xreg and newxreg are passed, the same covariates are applied to every series in the hierarchy.

A forecasted hierarchical/grouped time series of class gts.

Earo Wang and Rob J Hyndman

G. Athanasopoulos, R. A. Ahmed and R. J. Hyndman (2009) Hierarchical forecasts for Australian domestic tourism, International Journal of Forecasting, 25, 146-166.

R. J. Hyndman, R. A. Ahmed, G. Athanasopoulos and H.L. Shang (2011) Optimal combination forecasts for hierarchical time series. Computational Statistics and Data Analysis, 55(9), 2579–2589. http://robjhyndman.com/papers/hierarchical/

Hyndman, R. J., Lee, A., & Wang, E. (2014). Fast computation of reconciled forecasts for hierarchical and grouped time series. Working paper 17/14, Department of Econometrics & Business Statistics, Monash University. http://robjhyndman.com/working-papers/hgts/

Gross, C. and Sohl, J. (1990) Dissagregation methods to expedite product line forecasting, Journal of Forecasting, 9, 233-254.

hts, gts, plot.gts, accuracy.gts

forecast(htseg1, h = 10, method = "bu", fmethod = "arima")

## Not run: forecast(htseg2, h = 10, method = "comb", algorithms = "lu",
                  FUN = function(x) tbats(x, use.parallel = FALSE))
## End(Not run)