Table 1.

Simulation setup with equal weights: results for different $K$ under the standard prior (Sta), the normal gamma Prior (Ng), and when fitting an infinite mixture using the R package PReMiuM. Results are averaged over ten data sets

Prior	$K$	${\widehat{e}}_0$	$e_0$ fixed	${\widehat{K}}_0$	$M_0$	$M_{0,\mathit{\rho }}$	$MCR$	$MS{E}_{\mathit{\mu }}$
Sta	4	0.28		4	10000	0	0.049	0.167
	15	0.05		4	9802	0	0.049	0.167
	30	0.03		4	9742	0	0.048	0.168
Ng	4	0.28		4	10000	0	0.049	0.137
	15	0.06		5(6)	2845	0.85	0.050	$-$
	30	0.03		5(5)	2541	0.93	0.050	$-$
Ng	4		$0.01$	4	10000	0	0.047	0.136
	15		$0.01$	4	7465	0	0.048	0.137
	30		$0.01$	4(8)	4971	0	0.048	0.136
	30		$0.001$	4	9368	0	0.048	0.136
	30		$0.00001$	4	9998	0	0.047	0.136
PReMiuM		$\widehat{\mathit{\alpha }}$		$K^{est}$			$MCR$	$MS{E}_{\mathit{\mu }}$
		0.66		4			0.047	0.231