Skip to main content
. Author manuscript; available in PMC: 2018 Dec 21.
Published in final edited form as: Biostatistics. 2019 Jan 1;20(1):1–16. doi: 10.1093/biostatistics/kxx058

Table 2. RR of hospital admission: PM10 higher than 25 μg/m3 (chosen cut point) in Greater London. The main analysis with ≥5 subjects per wards is presented in bold, while the others are used as sensitivity analyses.

Areas Data used ≥1 subject
(12.9% missing)
 ≥5 subjects
(24.6% missing)
 ≥10 subjects
(37.4% missing)
 ≥20 subjects
(68.0% missing)
RR
95% CI		 (95% CI)
width		 RR
95% CI		 (95% CI)
width		 RR
95% CI		 (95% CI)
width		 RR
95% CI		 (95% CI)
width
i ∈ S X,C 0.91
(0.86–0.96)		 0.10 0.94
(0.89–1.00) 		0.11 0.96
(0.90–1.03)		 0.13 0.96
(0.88–1.04)		 0.16
X,C,EPS 1.04
(0.94–1.14)		 0.10 1.06
(1.01–1.12) 		0.12 1.07
(1.01–1.15)		 0.14 1.05
(0.95–1.16)		 0.21
i ∈ S ∪ I X,C 0.89
(0.84–0.94)		 0.10 0.89
(0.84–0.94) 		0.10 0.89
(0.84–0.94)		 0.10 0.89
(0.84–0.94)		 0.10
X,C,EPS 1.05
(0.99–1.12)		 0.13 1.02
(0.96–1.09) 		0.13 1.03
(0.97–1.10)		 0.13 1.06
(0.99–1.13)		 0.14
X,C,M
(MICE)		 0.98
(0.93–1.04)		 0.11 0.93
(0.88–0.99) 		0.11 0.92
(0.87–0.98)		 0.11 0.89
(0.84–0.94)		 0.10