Conditional logistic regression model predicting children's injury risk from child behaviour and environmental circumstances
| Model 1 | Model 2 | Model 3 | |
|---|---|---|---|
| Variable | OR (95% CI; n=2398) | OR (95% CI; n=2399) | OR (95% CI; n=2401) |
| Unusual circumstances (y/n) | 1.9*** (1.5 to 2.4) | 2.1*** (1.6 to 2.6) | – |
| Unusual child behaviour (y/n) | 3.0*** (1.9 to 4.5) | – | 3.7*** (2.3 to 6.1) |
| Supervision | – | 0.8*** (0.8 to 0.9) | 0.8*** (0.8 to 0.9) |
| Unusual circumstances*supervision | – | 0.9 (0.8 to 1.2) | – |
| Unusual child behaviour*supervision | – | – | 0.6* (0.3 to 1.0) |
*p<0.05. **p<0.01. ***p<0.001. For unusual circumstances and unusual child behaviour, 0=’no’ and 1=‘yes’. For injury risk, 0=control condition (non-injury event) and 1=injury event. Variables not entered in the model are marked as ‘–’. The reference category is 0.