I got a bit confused about RMSEC but I got how RMSECV and RMSEP are calculated and their meaning, though.
I am working based on 2 papers which summarize their results with RMSEC, RMSECV1, RMSECV2 and RMSEP (Calibration, CrossValidation1, CrossValidation2 and Prediction errors, respectively). I have 2 datasets (D1 and D2), so I apply 2 cross-validation approaches to D1 and got RMSECV1 and RMSECV2, Then I fit the model using the whole D1 and validate it using D2, so I got RMSEP. Am I right here?
Now I suppose RMSC is related with the model I just validated with D2. But is it RMSEC the error of using D1 on the model trained with D1?
- RMSECV1 and RMSECV2: split D1 (LOSO or K-fold), fit and crossvalidate. Calculate average of partial errors for each approach.
- RMSEP: fit with D1, validate with D2.
- RMSEC: fit with D1, validate with D1 (?)