Table 2.
Simple logistic regressions of ESCUW (vs no ESCUW) on performance in the individual components of each examination. The table shows b = loge(OR), OR (i.e. eb) and its 95% confidence interval, and the odds ratio for comparing the likelihood of ESCUW in candidates at the 2.5th percentile (i.e. 2 SDs below the population mean examination performance) and at the 97.5th percentile (i.e. 2 SDs above the mean performance). All b values for predictors are significant with p < 0.001
| Exam | Constant | b = loge(OR) | OR = eb (95% CI) |
OR for ESCUW 2.5th percentile to 97.5th percentile |
|---|---|---|---|---|
| MRCGP: AKT n = 27,561 |
− 4.364 | − 0.611 | 0.543× (0.500, 0.589) | 11.52× |
| MRCGP: CSA n = 17,365 |
− 4.533 | − 0.692 | 0.501× (0.447, 0.561) | 15.93× |
| MRCP(UK): Part 1 n = 37,358 |
− 4.645 | − 0.597 | 0.550× (0.501, 0.605) | 10.89× |
| MRCP(UK): Part 2 n = 28,285 |
− 4.786 | − 0.589 | 0.555× (0.487, 0.633) | 10.55× |
| MRCP(UK): PACES n = 27,040 |
− 4.716 | − 0.586 | 0.557× (0.504, 0.615) | 10.42× |