Skip to main content

Table 6 Estimates of ORSCL and ORMH (95% CI), and ORG (2.5–97.5pct): Japanese data on celecoxib-peripheral edema with study period = 168 and 336 days and Exposure Definition I

From: A novel weighting method to remove bias from within-subject exposure dependency in case-crossover studies

Study period 168 days 336 days
Days in 1 period 1 day 14 days 84 days 1 days 14 days 168 days
M 167 11 1 335 23 1
ORSCL 4.19 (3.16–5.55) 3.39 (2.58–4.45) 2.13 (1.54–2.95) 7.16 (5.27–9.74) 5.97 (4.43–8.05) 3.73 (2.42–5.75)
ORMH 2.45 (1.94–3.09) 2.38 (1.87–3.03) 2.13 (1.54–2.95) 2.95 (2.28–3.82) 2.92 (2.24–3.79) 3.73 (2.42–5.75)
ORG 2.45 (1.87–3.25) 2.38 (1.82–3.15) 2.13 (1.57–2.99) 2.95 (2.14–4.09) 2.92 (2.12–4.03) 3.73 (2.49–6.06)
  1. M is the number of control periods
  2. ORSCL: odds ratio by the standard conditional logistic regression; ORMH: odds ratio by the Mantel-Haenszel method; ORG: odds ratio by the Greenland’s method. 95%CI: 95% confidence interval; 2.5–97.5pct: 2.5 to 97.5 percentiles
Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us