simulated common Cochran-Mantel-Haenszel odds ratio for CUD. We did not require the total number of simulated CUD cases per stratum to match the observed numbers, because we wanted to keep this approach as elementary as possible. We repeated the simulation 100,000 times and compared the results with the observed odds ratio 0.728 for CUD, obtaining an estimator of the P-value for the null hypothesis with variance less than 1/(4x100000) = 0.0000025. This was repeated for various estimates of PRE among the six groups: a total of 212 combinations from the six sets PRESZ ∈ {0.6, 0.7, 0.8, 0.9}, PREBP ∈ {0.3, 0.4, 0.5, 0.6}, PREASD ∈ {0.05, 0.1, 0.15, 0.2}, PREADHD ∈ {0.1, 0.2, 0.3, 0.4}, PREMDD ∈ {0.2, 0.3, 0.4, 0.5} and PREICON ∈ {0.1, 0.15, 0.2, 0.25}. The largest P-value encountered was 8.69x10−3, making the the null hypothesis very unlikely.
