In the 2007 Romanian dissection experiment, the accuracy of the
prediction model was assessed using the root mean squared error of
prediction (RMSEP) calculated using the leave-one-out procedure on
the entire randomly selected sample. It should be noted that previous
EU regulation recommended that the accuracy of the prediction be estimated
using the residual standard deviation (RSD) of linear regression.
Thiswas later replaced by the root mean squared error (RMSE) in order
to incorporate the prediction error fromthe possible bias. RMSEP incorporates
both the prediction error fromresidual variation and the prediction
error from the estimation of the constant and the regression
coefficients. Consequently, the RMSEP is generally larger than the RSD