What is the difference between the "RMSE" and the validation "RMSE" in the Curve Fitting Toolbox?

5 views (last 30 days)
Hello,
I've been using the curve fitting toolbox to fix a set of point cloud data. In the goodness of fit evaluations, I can see two different RMSE: RMSE and Validation RMSE. Would someone please explain what's the difference between the two RMSEs and why they are different in value?
It feels like the "validation RMSE" is the RMSE error between the actual point cloud surface and the fitted surface. However, if this is the case, then what is the RMSE (or non-validation RMSE)? I can't find a detailed explaination online, so hope someone would help me. Thanks.

Answers (1)

Sulaymon Eshkabilov
Sulaymon Eshkabilov on 1 Aug 2021
Note that in your upper plot figure, your fit data is shown and "RMSE" computed for
and in the bottom one, some fit (validation) data set is taken for your computed fit model and "validation RMSE" is computed for that part of data.
  1 Comment
JZ0115
JZ0115 on 1 Aug 2021
Well, the bottom figure is the residual map, which is the fitted surface (blue and green) minus the original point cloud surface (the scattered points). So, when the toolbox said "validation", I don't know what it means. Isn't the RMSE already the RMS error of the difference between the fitted surface and the original surface?

Sign in to comment.

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!