Table 2. Mean ARI by Method and Factor Level.

Factor		KM	TA	RKM	FKM	PPK	PCAPP
# of Clusters	4	.30	.23	.39 (.23)	.21 (.12)	.06	.64*
	6	.24	.18	.31 (.19)	.15 (.14)	.07	.49*
	8	.23	.14	.24 (.16)	.15 (.12)	.06	.41*
# of True Variables	2	.14	.07	.16 (.16)	.11 (.10)	.04	.58*
	4	.19	.12	.27 (.19)	.15 (.12)	.06	.52*
	6	.22	.21	.33 (.23)	.18 (.16)	.07	.48*
	12	.46	.34	.46 (.34)	.24 (.21)	.08	.47*
# of Masking Variables	2	.36	.29	.45 (.27)	.29 (.20)	.11	.53*
	4	.29	.20	.36 (.24)	.18 (.14)	.18	.52*
	6	.22	.16	.28 (.19)	.13 (.12)	.13	.54*
	12	.15	.08	.16 (.08)	.08 (.06)	.02	.42*
Cluster Density	Equal	.26	.18	.32 (.17)	.11 (.12)	.04	.56*
	10%	.30	.19	.34 (.17)	.14 (.10)	.06	.51*
	60%	.20	.18	.28 (.25)	.26 (.17)	.09	.45*

Note: KM = K-means clustering; TA = Tandem Analysis; RKM = Reduced K-means; FKM = Factorial K-means; PPK = Projection Pursuit Kurtosis; PCAPP = Principal Cluster Axes Projection Pursuit. For FKM and RKM, the values in parantheses are the results from the multiple random restarts with 1,000 random restarts.