Statistical testing

While using adequate metrics to compare the accuracy of the forecasts is important, it is also necessary to analyze whether any difference in accuracy is statistically significant. This is paramount to conclude whether the difference in accuracy does really exist and it is not simply due to random differences between the forecasts.

• Diebold-Mariano test
  • DM test
  • plot_multivariate_DM_test
• Giacomini-White test
  • GW test
  • plot_multivariate_GW_test