Table A.2.

Prior sensitivity analysis, with estimates and 95% intervals for effect sizes with the prior from the manuscript, four additional priors, and an analysis with the convolution model parameterization of the spatial random effect from Riebler et al. (2016).

	Canada		Italy		England		United States
	Est	CI	Est	CI	Est	CI	Est	CI
Prior from manuscript$pr(\sigma >1)=0.5$, $\text{logit}\left(\rho \right)\sim \text{N}(0,1.8^2)$
NO${}_2$	5.0	(−3.8, 14.7)	2.7	(−0.4, 6.0)	0.5	(−0.5, 1.6)	2.3	(−3.2, 8.1)
PM2.5	−10.9	(−23.9, 4.5)	0.5	(−2.5, 3.5)	2.9	(−0.7, 6.6)	12.6	(7.4, 18.1)
Lung cancer	−0.2	(−2.3, 2.0)	0.0	(−0.9, 0.9)	0.7	(0.5, 1.0)	0.0	(−0.2, 0.2)
Unemployment	−19.0	(−25.1,−12.4)	−7.4	(−20.8, 8.6)	4.5	(−3.0, 12.7)	−4.3	(−6.0, −2.5)
Visible minorities	2.8	(0.5, 5.1)	2.3	(−0.2, 5.0)	1.1	(0.7, 1.5)	1.3	(1.1, 1.5)
$pr(\sigma >1)=0.2$, $\text{logit}\left(\rho \right)\sim \text{N}(0.75,1.8^2)$
NO${}_2$	4.9	(−3.6, 14.2)	2.5	(−0.5, 5.7)	0.5	(−0.4, 1.6)	2.5	(−3.1, 8.4)
PM2.5	−11.8	(−24.4, 2.9)	0.4	(−2.5, 3.5)	3.0	(−0.5, 6.7)	12.5	(7.3, 18.0)
Lung cancer	0	(−2.1, 2.1)	−0.1	(−1.0, 0.7)	0.7	(0.5, 1.0)	0	(−0.2, 0.2)
Unemployment	−18.7	(−24.9, −12.1)	−4.2	(−18.0, 11.6)	4.2	(−3.2, 12.2)	−4.2	(−6.0, −2.5)
Visible minorities	2.9	(0.7, 5.1)	2.2	(−0.3, 4.8)	1.1	(0.7, 1.6)	1.3	(1.1, 1.5)
$pr(\sigma >1)=0.2$, $\text{logit}\left(\rho \right)\sim \text{N}(-0.75,1.8^2)$
NO${}_2$	5.1	(−3.9, 15.2)	3.0	(−0.2, 6.3)	0.5	(−0.5, 1.6)	2.1	(−3.4, 7.9)
PM2.5	−9.7	(−23.1, 6.2)	0.5	(−2.6, 3.6)	2.8	(−0.9, 6.5)	12.8	(7.5, 18.2)
Lung cancer	−0.3	(−2.5, 1.9)	0.1	(−0.8, 1.0)	0.7	(0.5, 1.0)	0.0	(−0.2, 0.2)
Unemployment	−19.2	(−25.1, −12.8)	−11.0	(−23.5, 4.4)	4.8	(−2.8, 13.3)	−4.3	(−6.0, −2.5)
Visible minorities	2.7	(0.4, 5.0)	2.5	(−0.1, 5.2)	1.1	(0.6, 1.5)	1.3	(1.1, 1.5)
$pr(\sigma >1)=0.8$, $\text{logit}\left(\rho \right)\sim \text{N}(0.75,1.8^2)$
NO${}_2$	4.9	(−3.7, 14.4)	2.5	(−0.5, 5.7)	0.5	(−0.4, 1.6)	2.5	(−3.1, 8.3)
PM2.5	−11.8	(−24.6, 3.2)	0.4	(−2.5, 3.5)	3.0	(−0.5, 6.7)	12.5	(7.3, 18.0)
Lung cancer	0.0	(−2.1, 2.1)	−0.1	(−1.0, 0.8)	0.7	(0.5, 1.0)	0.0	(−0.2, 0.2)
Unemployment	−18.7	(−25.0, −12.0)	−4.2	(−18.0, 11.6)	4.2	(−3.2, 12.3)	−4.2	(−6.0, −2.5)
Visible minorities	2.9	(0.6, 5.1)	2.2	(−0.3, 4.8)	1.1	(0.7, 1.6)	1.3	(1.1, 1.5)
$pr(\sigma >1)=0.8$, $\text{logit}\left(\rho \right)\sim \text{N}(-0.75,1.8^2)$
NO${}_2$	5.2	(−3.9, 15.2)	3.0	(−0.2, 6.3)	0.5	(−0.5, 1.6)	2.2	(−3.3, 8.0)
PM2.5	−9.9	(−23.3, 6.0)	0.5	(−2.6, 3.6)	2.8	(−0.9, 6.5)	12.7	(7.5, 18.2)
Lung cancer	−0.3	(−2.4, 1.9)	0.1	(−0.8, 1.0)	0.7	(0.5, 1.0)	0.0	(−0.2, 0.2)
Unemployment	−19.2	(−25.2, −12.7)	−10.9	(−23.7, 4.9)	4.8	(−2.8, 13.3)	−4.3	(−6.0, −2.5)
Visible minorities	2.7	(0.4, 5.0)	2.5	(−0.1, 5.2)	1.1	(0.6, 1.5)	1.3	(1.1, 1.5)
Convolution model parameterization
NO${}_2$	3.9	(−6.0, 15.2)	3.9	(0.7, 7.3)	0.6	(−0.4, 1.7)	3.2	(−2.3, 8.9)
PM2.5	−8.6	(−23.7, 9.2)	1.9	(−1.2, 4.9)	3.3	(−0.3, 7.0)	12.0	(6.9, 17.4)
Lung cancer	0.1	(−2.2, 2.5)	0.0	(−0.9, 0.9)	0.7	(0.4, 0.9)	0.0	(−0.2, 0.2)
Unemployment	−20.6	(−26.9, −14.0)	−17.0	(−24.4, −8.6)	3.1	(−4.3, 10.9)	−4.1	(−5.8, −2.4)
Visible minorities	2.3	(−0.2, 4.9)	3.2	(0.5, 6.0)	1.2	(0.8, 1.7)	1.3	(1.1, 1.5)