Skip to main content
. Author manuscript; available in PMC: 2013 Nov 1.
Published in final edited form as: Stat Biosci. 2012 Nov 1;4(2):319–338. doi: 10.1007/s12561-012-9072-7

Fig. 2.

Fig. 2

Simulation results of size and power as a function of between-outcome correlation. The type I error was set at the 0.05 level. Four tests were compared. For SOS-CCA and Step-CCA, we considered the proposed Wilks’ Λ based tests. For PMA-CCA, we considered the canonical correlation based test of [23]. We also included the regular test without gene selection. For all of the methods, CIC was used as the model selection criteria.