Table 5.

The predictive ability of four basic methods and ELPGV, and the comparison p-value between ELPGV and others in mfp, my, scs with cattle dataset

Method	mfp		my		scs
	Predictive ability	p-value	Predictive ability	p-value	Predictive ability	p-value
ELPGV	0.8748 ± 0.0009	—	0.7959 ± 0.0016	—	0.7523 ± 0.0019	—
BayesA	0.8713 ± 0.0010	2.665E−31	0.7935 ± 0.0017	5.726E−19	0.7496 ± 0.0019	1.242E−23
BayesB	0.8739 ± 0.0009	2.356 E−10	0.7948 ± 0.0017	1.335E−07	0.7503 ± 0.0020	5.614E−11
BayesCπ	0.8632 ± 0.0010	5.884E−52	0.7928 ± 0.0017	1.026E−26	0.7518 ± 0.0019	0.001E−00
GBLUP	0.8259 ± 0.0013	9.943E−80	0.7809 ± 0.0017	5.133E−52	0.7482 ± 0.0019	3.801E−29

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

— Represents no explicit result was found in this method

mfp, milk fat percentage; my, milk yield; scs, somatic cell score