TABLE 1.

Comparison of Bayesian Shared Component Models with Spatial Conditionally Autoregressive Priors or Nonspatial Priors for the Random Effects Components

	Spatial	Nonspatial
Fixed components
Exp(αb): intercept (black)	1.8 (1.8–1.9)	1.9 (1.8–1.9)
Exp(αw): intercept (white)	0.86 (0.85–0.87)	0.85 (0.83–0.86)
δ: scaling parametera	0.62 (0.54–0.69)	0.62 (0.57–0.67)
Random effects
${\sigma }_{{\nu }_i}^2$: black-specific heterogeneity	0.03 (0.02–0.04)	0.02 (0.01–0.03)
${\sigma }_{u_i}^2\times {\delta }^2$: shared variation (black)	0.01 (0.00–0.01)	0.01 (0.00–0.01)
${\sigma }_{u_i}^2/{\delta }^2$: shared variation (white)	0.06 (0.05–0.06)	0.07 (0.06–0.07)
Proportion shared variation (black)	0.24 (0.14–0.36)	0.32 (0.23–0.42)
Model deviance information criteria	23900	25628

Values in parentheses represent the 95% credible intervals of the estimates. The OpenBUGS code to estimate the model parameters can be found in the eAppendix (http://links.lww.com/EDE/B58).

^aThe differential scaling of the shared random effect, v_i, for black and white infants is represented by δ.