What does the mean percentage error measure indicate?

The mean percentage error measure serves as a metric to assess the accuracy of forecasts by determining the average variance between actual and predicted values. It is calculated by taking the difference between the actual and predicted values, expressing this difference as a percentage of the actual values, and then averaging these percentage errors across all predictions.

This measure is particularly useful for understanding not just the magnitude of errors in predictions but also how these errors relate to the actual values, providing a perspective on the relative performance of the predictions. A lower mean percentage error indicates a better fit of the model to the actual observations, highlighting the effectiveness of the forecasting process.

Other options, while relevant to different aspects of error measurement, do not accurately define the mean percentage error. The average absolute value of error focuses on the magnitude of errors without regard to their direction or percentage of actual values. The sum of all prediction errors provides a raw total which can be misleading if positive and negative errors offset each other. The ratio of forecast to actual values does not capture the error but rather illustrates the relationship between predicted and actual figures.