. Author manuscript; available in PMC: 2017 Mar 1.

Published in final edited form as: J Stat Plan Inference. 2016 Mar 1;170:106–116. doi: 10.1016/j.jspi.2015.09.008

Table 6.

Constrained model with k₀ = 2 and x_i = i/n for i = 1,..., n. E(Y|x) = 1 + x – 0.5(x – 0.5)⁺ + (x – 0.7)⁺

n	Prob	σ = 0.5			σ = 0.02
n	Prob	BIC₂	BIC₃	MIC	BIC₂	BIC₃	MIC
30	$\hat{P} (\hat{κ} < k_{0})$ $\hat{P} (\hat{κ} = k_{0})$ $\hat{P} (\hat{κ} > k_{0})$	$0.58 \overset{‒}{6}$ $0.36 \overset{‒}{3}$ 0.050	0.860 0.140 0	$0.85 \overset{‒}{3}$ $0.14 \overset{‒}{6}$ 0	0 0.920 0.080	$0.02 \overset{‒}{6}$ $0.95 \overset{‒}{6}$ $0.01 \overset{‒}{6}$	$0.02 \overset{‒}{3}$ 0.960 $0.01 \overset{‒}{6}$
50	$\hat{P} (\hat{κ} < k_{0})$ $\hat{P} (\hat{κ} = k_{0})$ $\hat{P} (\hat{κ} > k_{0})$	$0.50 \overset{‒}{3}$ $0.43 \overset{‒}{3}$ $0.06 \overset{‒}{3}$	$0.81 \overset{‒}{6}$ $0.18 \overset{‒}{3}$ 0	0.890 0.110 0	0 $0.89 \overset{‒}{3}$ $0.10 \overset{‒}{6}$	$0.01 \overset{‒}{3}$ $0.96 \overset{‒}{3}$ $0.02 \overset{‒}{3}$	0.020 $0.96 \overset{‒}{6}$ $0.01 \overset{‒}{3}$
150	$\hat{P} (\hat{κ} < k_{0})$ $\hat{P} (\hat{κ} = k_{0})$ $\hat{P} (\hat{κ} > k_{0})$	$0.09 \overset{‒}{3}$ $0.86 \overset{‒}{3}$ $0.04 \overset{‒}{3}$	0.280 $0.71 \overset{‒}{3}$ $0.00 \overset{‒}{6}$	0.530 0.470 0	0 $0.93 \overset{‒}{3}$ $0.06 \overset{‒}{6}$	0 $0.99 \overset{‒}{6}$ $0.00 \overset{‒}{3}$	0 1 0