A hierarchical spike-and-slab model for pan-cancer survival using pan-omic data

BMC Bioinformatics

Table 3 Mean sum of squared deviations for each model under each data-generating condition. Row names correspond to the pattern of covariate inclusion. Column names correspond to the models. Bolded values indicate the best performing model based on a pairwise t-test. If multiple values are bolded, then model performances were not significantly different at 0.01 level

	Hierarchical	Fixed (0.5)	Full model	Shared	Null model	Joint	Separate
All In (Prob = 0.5)	0.0307	0.1124	0.4927	0.1507	0.5073	0.0644	0.0975
All In (Prob = 0.1)	0.0251	0.1204	0.8990	0.0411	0.1010	0.0314	0.0796
Indep. In (Prob = 0.5)	0.0915	0.0854	0.5000	0.0854	0.5000	0.4002	0.0977
Indep. In (Prob = 0.1)	0.0366	0.0813	0.8987	0.0269	0.1013	0.2424	0.0625
All In	0.0529	0.1304	0.0000	0.0016	1.0000	0.0981	0.1431
None In	0.0162	0.1103	1.0000	0.0002	0.0000	0.0211	0.0637

Bold values indicate the best performing model for each scenario, and multiple values are bolded if they are not significantly different from the best model at the 0.01 level

ISSN: 1471-2105