Table 1.

(a) For each scenario, mean and standard deviation of RMSE across 500 simulated data sets under the proposed BNP method, the naive Bayesian method (Naive), and the LinearDDP method. Bold values indicate that the proposed BNP yields the smallest mean RMSE when . (b) Means and standard deviations of RMSE for estimating across 500 simulations in three scenarios under the proposed BNP approach, the naive Bayesian method (Naive), and the LinearDDP method, respectively

Scenario
	BNP	Naive	LinearDDP	BNP	Naive	LinearDDP
1	0.012 (0.007)	0.013 (0.007)	0.014 (0.007)	0.012 (0.006)	0.013 (0.007)	0.015 (0.008)	(a)
2	0.042 (0.022)	0.088 (0.032)	0.063 (0.020)	0.019 (0.007)	0.073 (0.035)	0.058 (0.023)
3	0.012 (0.006)	0.013 (0.007)	0.014 (0.007)	0.012 (0.007)	0.014 (0.007)	0.016 (0.008)

Scenario
	BNP	Naive	LinearDDP	BNP	Naive	LinearDDP
1	0.286 (0.087)	0.328 (0.126)	0.332 (0.087)	0.059 (0.035)	0.073 (0.051)	0.091 (0.016)
2	0.277 (0.128)	0.493 (0.250)	0.449 (0.189)	0.090 (0.062)	0.199 (0.169)	0.179 (0.123)
3	0.106 (0.032)	0.105 (0.038)	0.115 (0.043)	0.033 (0.016)	0.035 (0.021)	0.043 (0.027)

Scenario
	BNP	Naive	LinearDDP
1	0.185 (0.037)	0.207 (0.047)	0.181 (0.042)	(b)
2	0.261 (0.070)	0.243 (0.111)	0.203 (0.084)
3	0.086 (0.028)	0.097 (0.034)	0.086 (0.035)