Table 3.
Geometric mean values of hazard ratios associated with predictors of initial SSTI over 100 simulations in univariate and multivariate Cox regression models with an interaction term
| Factor | Model 12 | Model 13 |
|---|---|---|
| CD4 <200 cells/ml | 3·02 | 3·02 |
| HIV viral load <1000 copies/ml | 0·51 | 0·51 |
| TMP-SMX prescription | ||
| If HIV viral load ⩾1000 copies/ml | 0·93 | |
| If HIV viral load <1000 copies/ml | 0·69 | |
| TMP-SMX use | ||
| If HIV viral load ⩾1000 copies/ml | 0·70 | |
| If HIV viral load <1000 copies/ml | 0·69 |
TMP-SMX, Trimethoprim-sulfamethoxazole; SSTI, skin and soft tissue infection.
Results of various Cox regression modelling strategies utilizing interaction terms applied to our simulated dataset. We see that model 12, which introduces an interaction between HIV viral load and TMP-SMX prescription to model 7, corrects much of the bias seen in that model. Model 13, which introduces an interaction between HIV viral load and TMP-SMX prescription to model 1, preserves the unbiased nature of that model.