Table 2. Model diagnostics and variance components of structured and unstructured spatial function in three breast cancer indicators.
Early-stage incidence | Advanced-stage incidence | Mortality | ||||
VCM | REM | VCM | REM | VCM | REM | |
D(θ) | 4203.80 | 4201.45 | 4200.53 | 4196.55 | 4201.14 | 4200.83 |
pd | 216.34 | 222.74 | 210.89 | 213.09 | 211.87 | 212.61 |
DIC | 4420.14 | 4424.19 | 4411.42 | 4409.64 | 4413.01 | 4413.44 |
(95% CI) | 2.26 | 3.96 | 3.18 | 1.62 | 0.85 | 2.16 |
(0.76, 4.62) | (1.92, 6.29) | (1.25, 5.64) | (0.43, 3.86) | (0.22, 1.84) | (0.97, 3.94) | |
(95% CI) | 0.56 | 0.42 | 0.43 | 0.64 | 0.78 | 0.52 |
(0.02, 1.02) | (0.003, 1.03) | (0.004, 0.94) | (0.09, 1.09) | (0.46, 1.11) | (0.14, 0.96) | |
0.80 | 0.90 | 0.88 | 0.72 | 0.52 | 0.81 |
Abbreviation: VCM = varying-coefficient model; REM = random-effects model, D(θ) = posterior mean of the deviance; pd = effect number of parameters; = structured spatial variance; = unstructured spatial variance; = proportion of the structured spatial variance in total spatial variance.