Skip to main content
. Author manuscript; available in PMC: 2016 Oct 19.
Published in final edited form as: Stat Med. 2016 Jan 5;35(14):2467–2478. doi: 10.1002/sim.6844

Table II.

Results as Published vs. DL (1986) vs. SGS (2012). Entries in columns 3–5 are Point Estimate of Relative Risk (95% CI) {2-sided P-value}; cc=continuity corrections for zero-event cells; DL is calculated from Comprehensive Meta-Analysis version 2.0 and also employs standard continuity corrections for zero-event cells.

Ref from Table I Method As Published DL SGS Ratio Lengths DL:SGS
13 DL (cc) 1.7 (1.12.7){0.017} 1.73 (1.112.70) 2.13 (1.323.44){0.003} 0.75
14 DL (cc) 0.58 (0.50–0.68){<0.001} 0.58 (0.49–0.68) 0.58 (0.49–0.68){<0.001} 1.00
15 DL 0.80 (0.69–0.94){0.006} 0.81 (0.69–0.94) 0.79 (0.68–0.92){0.005} 1.04
16 Fixed 1.33 (1.13–1.56){<0.001} 1.35 (1.14–1.58) 1.36 (1.15–1.61){0.002} 0.96
17.1 Fixed (cc) 0.33 (0.23–0.47){<0.001} 0.41 (0.30–0.56) 0.39 (0.28–0.55) {0.001} 0.96
17.2 Fixed(cc) 0.64 (0.460.86){0.007} 0.71 (0.550.93) 0.70 (0.441.11) {0.11} 0.57
18.1 Fixed 0.93 (0.79–1.10){0.41} 0.94 (0.79–1.10) 0.94 (0.80–1.10) {0.36 } 1.03
18.2 DL (cc) 0.69 (0.56–0.84){<0.001} 0.69 (0.56–0.84) 0.72 (0.59–0.88){0.004} 0.97
19.1 DL(cc) 0.79 (0.65–0.95) {0.01} 0.79 (0.65–0.95) 0.78 (0.68–0.90){0..001} 1.36
19.2 DL(cc) 1.39 (1.00–1.95) {0.053} 1.40 (1.00–1.95) 1.40 (1.00–1.98){0.052} 0.97
20 DL(cc) 1.33 (0.95–1.86) {0.094} 1.33 (0.95–1.86) 1.42 (0.99–2.06){0.058} 0.85
21 DL(cc) 0.96 (0.91–1.02), {0.17} 0.96 (0.91–1.02) 0.96 (0.91–1.01){0.097} 1.10
22.1 DL (cc) 1.58 (1.21–2.06) {0.001} 1.57 (1.19–2.06) 1.60 (1.28–2.01){0.001} 1.16
22.2 Fixed 1.73 (1.27–2.36){<0.001} 1.71 (1.26–2.33) 1.74 (1.31–2.31){0.008} 1.07
23.1 DL 0.57 (0.390.82) {0.003} 0.57 (0.390.82) 0.54 (0.320.91){0.032} 0.73
23.2 DL 0.81 (0.361.83) {0.61} 0.81 (0.361.83) 0.77 (0.193.03){0.58} 0.52
24 DL 0.93 (0.85–1.03){0.15} 0.93 (0.85–1.03) 0.93 (0.84–1.03){0.15} 0.95
25 DL 1.07 (1.001.14){0.05} 1.07 (1.001.14) 1.07 (1.021.12)) {0.009} 1.40

Studies where DL and SGS differ substantially are highlighted.