Skip to main content
. 2006 May 20;2(1):41–52. doi: 10.1007/s11306-006-0018-2

Figure 3.

Figure 3.

Optimal number of principal components in the PCR and PLS models for varying sizes of training data set. Larger training sets allow more principal components to be included in the model to capture the finer details of the system. ANN models typically required fewer principal components than PCR and PLS models.