Dynamic Localized SNV, Peak SNV, and Partial Peak SNV: Novel Standardization Methods for Preprocessing of Spectroscopic Data Used in Predictive Modeling

Table 2

Summary of the model performances described by the mean value and the standard deviation of the RMSEP values during cross validation. The relative improvements and respective p-values compared with LSNV are also listed.

Method	Friction modifier ATF A		Antioxidant ATF B
	Transmission	Absorbance	Transmission	Absorbance
Raw	0.83 ± 0.22	0.53 ± 0.16	0.90 ± 0.14	0.70 ± 0.11
Single SNV	0.34 ± 0.14	0.42 ± 0.17	0.61 ± 0.11	0.70 ± 0.13
LSNV	0.30 ± 0.07	0.31 ± 0.07	0.24 ± 0.04	0.24 ± 0.04
DLSNV	0.28 ± 0.06	0.26 ± 0.05	0.21 ± 0.04	0.21 ± 0.04
Rel. improvement	9% ()	16% ()	13% ()	13% ()
PSNV	0.28 ± 0.08	0.28 ± 0.06	0.33 ± 0.06	0.31 ± 0.07
Rel. improvement	8% ()	9% ()	−41% ()	−33% ()
PPSNV	0.26 ± 0.06	0.26 ± 0.06	0.17 ± 0.04	0.24 ± 0.05
Rel. improvement	13% ()	15% ()	29% ()	−3% ()