crossv_ts: Time series cross-validation

In malexan/forecastbox: Toolbox of forecasting algorithms wrapped in web application

Description

Computes the forecast errors obtained by applying forecastfunction to subsets of the time series y using a rolling (accumulating) forecast origin. It differs from forecast::tsCV by skipping head of the time series.

Usage

crossv_ts(y, forecastfunction, h = 1, tail2CV = NULL, ...)

Arguments

y	Time series object.
forecastfunction	Forecasting function. It must be able take ts object as first parameter and h (forecasting horizon) as second parameter.
h	Forecast horizon.
tail2CV	Integer. It specifies number of time series elements for those predicitions will be build.
...	Additional parameters to forecastfunction.

Value

A time series object containing absolute prediction errors.

malexan/forecastbox documentation built on May 29, 2019, 3:44 a.m.