. Author manuscript; available in PMC: 2016 Aug 11.

Published in final edited form as: Spat Spatiotemporal Epidemiol. 2015 Aug 11;0:45–54. doi: 10.1016/j.sste.2015.08.001

Table 3.

Fitted model description.

Model	Description
F1	log (θ_i) = a₀ + a₁x_1i + a₂x_2i a_j ~ Norm(0, τ_α) where τ_α is fixed
F2	log (θ_i) = a₀ + a₁x_1i + a₂x_2i + u_i a_j ~ Norm(0, τ_α), where τ_α is fixed u_i ~ Norm(0, τ_u), τ_u ~ Gam(1,5e – 05)
F3	log (θ_i) = a₀ + a₁x_1i + a₂x_2i + u_i + v_i a_j ~ Norm(0, τ_α), where τ_α is fixed u_i ~ Norm(0, τ_u), τ_u ~ Gam(1,5e – 05) v_i ~ CAR (τ_v), τ_v ~ Gam(1,5e – 05)
F4	log (θ_i) = a₀ + a₁x_1i + a₂x_2i + a₃x_3i + a₄x₄₁ a_j ~ Norm(0, τ_α), where τ_α is fixed
F5	log (θ_i) = a₀ + a₁x_1i + a₂x_2i + a₃x_3i + a₄x₄₁ + u_i + v_i a_j ~ Norm(0,τ_α), where τ_α is fixed u_i ~ Norm(0,τ_u), τ_u ~ Gam(1,5e – 05) v_i ~ CAR(τ_v), τ_v ~ Gam(1,5e – 05)
F6	log (θ_i) = a₀ + u_i + v_i a_j ~ Norm(0,τ_α), where τ_α is fixed u_i ~ Norm(0,τ_u), τ_u ~ Gam(1,5e – 05) v_i ~ CAR (τ_v), τ_v ~ Gam (1,5e –05)