Table 6.

The predictive ability of four basic methods and ELPGV, and the comparison p-value between ELPGV and others in GY with wheat dataset

Method	The first place		The second place		The third place		The fourth place
	Predictive ability	p-value	Predictive ability	p-value	Predictive ability	p-value	Predictive ability	p-value
ELPGV	0.5273 ± 0.0104	—	0.5092 ± 0.0101	—	0.4050 ± 0.0102	—	0.4722 ± 0.0101	—
BayesA	0.5231 ± 0.0105	1.550E−10	0.5057 ± 0.0101	1.238E−07	0.3953 ± 0.0103	3.711E−15	0.4676 ± 0.0102	7.265E−14
BayesB	0.5080 ± 0.0104	2.296E−17	0.4947 ± 0.0104	5.993E−12	0.3914 ± 0.0101	4.098E−06	0.4542 ± 0.0101	1.261E−18
BayesCπ	0.5215 ± 0.0105	7.965E−19	0.5046 ± 0.0101	6.695E−11	0.3947 ± 0.0102	2.264E−17	0.4672 ± 0.0102	1.200E−13
GBLUP	0.5251 ± 0.0105	2.297E−04	0.5058 ± 0.0100	7.877E−07	0.3954 ± 0.0104	2.938E−12	0.4698 ± 0.0102	5.013E−05

ELPGV is the ensemble learning based on BayesA, BayesB, BayesCπ and GBLUP

— Represents no explicit result was found in this method