Table 5. Predictive performance of different approaches based on the binary transformation for dataset 1.

	Dataset 1, including random effect W			Dataset 1, excluding random effect W
Method	ER (SD)	AUC (SD)	AUPRC (SD)	ER (SD)	AUC (SD)	AUPRC (SD)
LASSO	0.43 (0.06)	0.56 (0.06)	0.56 (0.13)	0.44 (0.06)	0.56 (0.05)	0.55 (0.13)
ZINB+GLM	0.38 (0.06)	0.62 (0.06)	0.62 (0.12)	0.39 (0.06)	0.6 (0.06)	0.61 (0.12)
TPNB+GLM	0.38 (0.06)	0.63 (0.07)	0.63 (0.13)	0.38 (0.06)	0.62 (0.06)	0.62 (0.13)
NB+GLM	0.37 (0.06)	0.63 (0.07)	0.64 (0.12)	0.38 (0.06)	0.62 (0.07)	0.62 (0.13)
ZINB+LASSO	0.37 (0.06)	0.63 (0.06)	0.63 (0.12)	0.39 (0.06)	0.6 (0.06)	0.61 (0.12)
TPNB+LASSO	0.38 (0.06)	0.63 (0.07)	0.63 (0.13)	0.38 (0.06)	0.62 (0.06)	0.62 (0.13)
NB+LASSO	0.37 (0.06)	0.64 (0.06)	0.64 (0.13)	0.38 (0.06)	0.62 (0.07)	0.62 (0.13)