The square root of the average squared differences between measurements from a criterion device and those from a gold-standard device (e.g., CMJ jump height measured using the Output Sports IMU as the criterion device versus a lab-based force plate system as the gold-standard measurement). RMSE is more sensitive to larger measurement errors between the two devices than Mean Absolute Error (MAE) . Lower RMSE values indicate greater accuracy of the criterion device relative to the gold-standard device for capturing that performance metric (e.g., CMJ jump height). Higher RMSE values indicate lower accuracy of the criterion device relative to the gold-standard device for capturing that performance metric.

📋References

1. Willmott C, Matsuura K. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Research. 2005;30(1):79–82.

<aside>

🏠 Back to Output Sports Validity and Reliability Homepage

</aside>