Table 4.

Average misclassification error rates for the optimal designs obtained under the classification approaches using trees or random forests and for the equispaced designs for the macrophage model. The average misclassification error rates were calculated by repeating the random forest classification procedure 100 times and taking the average. The standard deviations are given in parentheses

Design	$n=1$	$n=2$	$n=3$	$n=4$	$n=5$
Tree	0.1928	0.1323	0.1433	0.1469	0.1483
	(0.0024)	(0.0021)	(0.0022)	(0.0019)	(0.0022)
RF	0.1925	0.1325	0.1408	0.1410	0.1465
	(0.0022)	(0.0021)	(0.0022)	(0.0021)	(0.0021)
Equi	0.2442	0.1974	0.1928	0.1912	0.1935
	(0.0027)	(0.0023)	(0.0023)	(0.0025)	(0.0024)