Chapter 5 The forecaster’s toolbox
In this chapter, we discuss some general tools that are useful for many different forecasting situations. We will describe some benchmark forecasting methods, methods for checking whether a forecasting method has adequately utilised the available information, techniques for computing prediction intervals,
Each of the tools discussed in this chapter will be used repeatedly in subsequent chapters as we develop and explore a range of forecasting methods.
Evaluating the accuracy of forecasts is essential in understanding a forecasting method’s strengths and weaknesses for particular data scenarios. Identifying the best method for the data is necessary in producing good forecasts.
In this chapter, we show some diagnostic tools which can be used to check that a forecasting method has adequately utilised the available information. Additionally, we discuss some accuracy measures that can be used to compare the forecasting performance across multiple models, and the difference in computing these measures on training data, with a test set, and using cross-validation.