How to Group Genes according to Expression Profiles?

Table 5

Estimated means, standard error, and lower (LB) and upper boundaries (UB) of a 95% confidence interval for the bias for each combination of method (𝑀) and number of genes (𝐺). The table is sorted in descending order of bias within each level of 𝐺. True number of clusters: 𝑘=2. Clustering algorithm: complete linkage.

𝑀	𝐺	Mean bias	Standard error	LB (95%)	UB (95%)
HOPACHm	100	14.93	2.08	10.85	19.01
HOPACHc	100	11.14	2.08	7.05	15.22
Gap	100	3.11	0.22	2.69	3.54
H	100	1.93	0.22	1.51	2.35
CH	100	0.68	0.22	0.26	1.10
Silh	100	0.45	0.22	0.03	0.88
CCC	100	0.16	0.22	−0.26	0.58
CCCm	100	0.16	0.22	−0.26	0.58
gDGC	100	0.05	0.22	−0.38	0.47
MClust	100	−0.05	0.22	−0.47	0.38
HOPACHm	300	8.16	2.08	4.08	12.24
H	300	6.41	0.22	5.99	6.83
Gap	300	4.77	0.22	4.35	5.20
HOPACHc	300	3.95	2.08	−0.13	8.04
CH	300	0.11	0.22	−0.31	0.54
gDGC	300	0.09	0.22	−0.33	0.51
Silh	300	0.07	0.22	−0.35	0.49
CCC	300	0.02	0.22	−0.40	0.45
CCCm	300	0.02	0.22	−0.40	0.45
MClust	300	−0.02	0.22	−0.45	0.40