Table 1.

Sensitivity of parameter estimates for the Bayesian point process model with different number of knots. Results for the areal Poisson model are also shown for comparison; in this aggregate data model, “distance” is the distance from the centroid of the census tract to nearest treatment facility, “age” is the mean observed age, and “late” is the proportion of late diagonosed patients within each census tract.

	Point Process Models			Poisson Model
	64 knots	200 knots	256 knots	(areal)
colorectal:
intercept	−8.65 (−8.87,−8.48)	−7.97 (−8.17,−7.72)	−8.02 (−8.12,−7.77)	−6.30 (−6.58,−6.02)
distance	−0.04 (−0.07,−0.01)	−0.17 (−0.20,−0.14)	−0.16 (−0.19,−0.13)	0.03 (−0.01,0.07)
poverty	−0.97 (−1.83,−0.22)	−1.06 (−1.84,−0.25)	−1.09 (−1.81,−0.31)	−0.99 (−1.93,−0.06)
age	0.25 (0.23,0.27)	0.25 (0.23,0.27)	0.25 (0.23,0.27)	0.06 (−0.04,0.16)
late	0.05 (−0.04,0.14)	0.05 (−0.04,0.14)	0.06 (−0.03,0.14)	−0.05 (−0.32,0.21)
prostate:
intercept	−6.40 (−6.62,−6.29)	−5.76 (−5.89,−5.62)	−5.80 (−6.03,−5.58)	−5.06 (−5.24,−4.84)
distance	−0.11 (−0.13,−0.08)	−0.25 (−0.27,−0.24)	−0.23 (−0.26,−0.20)	0.01 (−0.02,0.04)
poverty	−2.97 (−3.59,−2.38)	−3.32 (−3.97,−2.63)	−3.25 (−4.01,−2.71)	−2.85 (−3.55,−2.15)
age	0.25 (0.24,0.27)	0.26 (0.24,0.27)	0.25 (0.24,0.27)	−0.03 (−0.17,0.11)
late	−1.65 (−1.73,−1.58)	−1.65 (−1.73,−1.58)	−1.65 (−1.72,−1.59)	−0.08 (−0.45,0.29)
ρ	0.93 (0.90,0.97)	0.95 (0.91,0.99)	0.96 (0.90,0.99)	0.76 (0.59,0.87)
${\sigma }_1^2$	0.62 (0.44,0.89)	2.91 (2.34,3.57)	2.95 (2.25,3.70)	0.71 (0.52.0.96)
${\sigma }_2^2$	1.46 (1.02,2.07)	4.05 (3.19,4.97)	3.92 (2.15,4.88)	0.82 (0.49,1.21)