updateForecast: Update Analysis of Forecast Errors

In grundy95/changepoint.forecast: Sequential Changepoint Detection of Forecast Errors

Description

This function updates the analysis in a cptFor object with new forecast errors. This allows for the online implementation of the method as new forecast errors become available.

Usage

updateForecast(newErrors, model)

Arguments

newErrors	numeric vector. New Forecast errors to perform changepoint analysis upon.
model	cptFor object. Output of call to function cptForecast where initial forecast errors were analysed.

Details

This function can be embedded within a framework to allow for the sequential analysis of forecast errors as new data becomes available. Say you receive a new forecast error each day then this function can be used to update the analysis and then a flag can be created to signal when a changepoint has been detected by monitoring the tau and tau2 slots.

Value

An object of class cptFor

Examples

ans = cptForecast(stats::rnorm(500), m=300)
ans = updateForecast(stats::rnorm(10, 3), model=ans)
summary(ans)
plot(ans)

grundy95/changepoint.forecast documentation built on Dec. 20, 2021, 1:45 p.m.