Table 1 Hypothetical distribution of subjects according to the predictors and outcome incidence
From: A simple method for estimating relative risk using logistic regression
High incidence (50%) | Intermediate incidence (20%) | Low incidence (5%) | |||||
|---|---|---|---|---|---|---|---|
Independent Variable | Cases (n = 500) | Non-cases (n = 500) | Cases (n = 200) | Non-cases (n = 800) | Cases (n = 50) | Non-cases (n = 950) | Total (n = 1000) |
Predictor A | |||||||
positive | 409 | 191 | 161 | 439 | 45 | 555 | 600 |
negative | 91 | 309 | 39 | 361 | 5 | 395 | 400 |
Predictor B | |||||||
positive | 398 | 102 | 159 | 341 | 36 | 464 | 500 |
negative | 102 | 398 | 41 | 459 | 14 | 486 | 500 |
Predictor C | |||||||
positive | 227 | 173 | 84 | 316 | 23 | 377 | 400 |
negative | 273 | 327 | 116 | 484 | 27 | 573 | 600 |