Which error measure should I be using?

CB Predictor 1.0 has 3 error measure that it can use to calculate which method works best for your data: RMSE (root mean squared error), MAPE (mean absolute percentage error), and MAD (mean absolute deviation). All three of these measures are acceptable and standard. Which error measure you use usually depends on which measure is used most in your industry or company, so that you can accurately compare your forecasts with others in your office or field.

If no error measure standard seems to apply, you can use the default (RMSE) or see the descriptions of the different error measures in Chapter 2 of the CB Predictor User Manual to help you decide for yourself.