Holt's trend methods
Holt's local trend method is implemented in the holt()
function:
> holt(y, h = 10, ...)
Here, you will apply it to the austa
series, which contains annual counts of international visitors to Australia from 1980-2015 (in millions). The data has been pre-loaded into your workspace.
This exercise is part of the course
Forecasting in R
Exercise instructions
- Produce 10 year forecasts of
austa
using Holt's method. Seth
accordingly. - Use the
summary()
function to view the model parameters and other information. - Plot your forecasts using the standard time plotting function.
- Use
checkresiduals()
to see if the residuals resemble white noise.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Produce 10 year forecasts of austa using holt()
fcholt <- ___
# Look at fitted model using summary()
___
# Plot the forecasts
___
# Check that the residuals look like white noise
___