Effect of stringency of feature dimensionality reduction on predictor construction. Probe set selection between IgA and IgG heavy chain-expressing MM patient groups over a wide range of P
values (from .05 to .37, different colors). The number of selected probe sets has no effect on the length and content of the resulting predictor after deletions with a P
value equal to or less than .01 divided by the list length for Bonferroni correction, while the computational time (standard desktop computer) is strikingly reduced. Close circles: f function or overall strength of interclass comparisons on the left vertical scale. Open circles: X2 or min, or smallest strength of all interclass comparisons on the right vertical scale. The number of non-significant interclass comparisons NS is null here.