Classification based on extensions of LS-PLS using logistic regression: application to clinical and multiple genomic data

Table 1 Rates of convergence (%) from the 100 simulated data sets for the five methods, according to different κ_max:1,4 and 8

κ _max	R-PLS	LS-PCR	LS-PLS-IRLS	R-LS-PLS	IR-LS-PLS
1	100	100	71	100	22
4	100	100	41	100	76
8	100	99	44	100	78

R-PLS denotes the results from the analysis of gene expression alone. LS-PCR denotes the approach derived from PCR, where gene expression data are analyzed using PCA and IRLS can thus be applied to the merged data set of PCA scores and clinical data. LS-PLS-IRLS, R-LS-PLS, and IR-LS-PLS denote the rates of convergence from the newly proposed approaches combining expression and clinical data. The number of gene expression variables to preselect p_red is set to 500 in the SIS procedure

ISSN: 1471-2105