In this paper we introduce discriminant Q2 (DQ2) as an improvement for the Q2 value used in the validation of PLSDA models. DQ2 does not penalize class predictions beyond the class label value. With rigorous Monte Carlo simulations we show that when DQ2 is used, a smaller effect can be found statistically significant than when the standard Q2 is used.
Authors from the NMC:
Publication data (text):
2008
DOI:
10.1007/s11306-008-0126-2
Pages:
2008; 4 (4): 293-296
Published in:
Metabolomics
Date of publication:
December, 2008
Status of the publication:
Published/accepted
Link to publication: