A scorecard is a straightforward way to identify patterns in the difference of performance between two configurations, including level of significance for specified metrics, variables, thresholds, regions, and times. The figure below shows a scorecard for Equitable Threat Score (ETS) over the CONUS, comparing the performance of Suite 2 versus Suite 1. The cells on the table are marked green for the forecast lead times and thresholds for which Suite 2 is better than Suite 1, and marked red for those that are worse. Grey shaded boxes indicate no statistically significant differences.

More results can be found at:
Tar file of scorecard results