Whole data analysis | 200 CVs | ||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|

Models | Models components | Estimated variance (90% posterior confidence region) | Log likelihood^{e} | Effective number of parameters (pD) | Deviance information criteria (DIC) | Average CV-AUC^{f} | Proportion of times model in column had AUC > model in row | ||||||

COV^{a} | METH^{b} | WGGE^{c} | METH × WGGE^{d} | METH | WGGE | METH × WGGE | COV + METH + WGGE | COV + METH × WGGE | |||||

COV | X | — | — | — | −85.7 | 6.4 | 177.9 | 0.724 (0.001)^{g} | >0.99 | >0.99 | |||

COV + METH + WGGE | X | X | X | 0.162 (0.075; 0.440) | 0.220 (0.090; 0.690) | — | −73.9 | 17.6 | 165.4 | 0.754 (0.004)^{h} | — | 0.40 | |

COV + METH × WGGE | X | X | X | X | 0.101 (0.046; 0.272) | 0.138 (0.055; 0.474) | 0.101 (0.044; 0.329) | −69.9 | 20.2 | 159.9 | 0.753 (0.005)^{h} | — | — |

a Age: African American Y/N; lobular (Y/N); and tumor subtype.

b Methylation.

c Whole-genome RNA-seq.

d Methylation-by-WGGE.

e Estimated posterior mean of the log likelihood.

f Average over 200 tenfold CVs.

g,h The same letter indicates that the models are no different (empirical

*P*< 0.05).