Table 2

Unadjusted and adjusted logisitic regression models using the first-reported lifetime number of partners (Q1), the second-reported lifetime number of partners (Q2), and the maximum of the first and second responses and odds of HSV-2 seropositivity
Model A* Model B* Model C*
Unadjusted Adjusted ** Unadjusted Adjusted ** Unadjusted Adjusted **
OR (95% CI) OR (95% CI) OR (95% CI) OR (95% CI) OR (95% CI) OR (95% CI)
Men 1.10 (1.02, 1.19) 1.08 (1.00, 1.18) 1.13 (1.05, 1.22) 1.11 (1.02, 1.21) 1.13 (1.04, 1.22) 1.11 (1.02, 1.21)
Women 1.33 (1.20, 1.47) 1.30 (1.17, 1.44) 1.35 (1.22, 1.49) 1.33 (1.20, 1.47) 1.37 (1.24, 1.51) 1.35 (1.22, 1.49)
CLR 1.17 (M); 1.22 (W) 1.18 (M); 1.23 (W) 1.17 (M); 1.22 (W) 1.18 (M); 1.22 (W) 1.17 (M); 1.22 (W) 1.18 (M); 1.22 (W)
AIC 517.83 484.98 511.27 480.25 510.10 478.65
AUC 0.66 0.74 0.67 0.74 0.67 0.75

Abbreviations: OR: Odds ratio; CI: confidence interval; HSV-2: herpes simplex virus type 2; CLR: confidence limit ratio; AIC: Akaike information criterion; AUC: area under the receiver operating characterictic curve; M: men; W: women.

* Model A uses Q1 as the independent variable; Model B uses Q2 as the independent variable; Model C uses the maximum of Q1 and Q2 as the independent variable. All models are based on records with no missing value for Q1, Q2, sex, age, mode of survey administration and HSV-2 seropositivity.

** Adjusted for age and mode of survey administration.

Norris Turner et al.

Norris Turner et al. BMC Medical Research Methodology 2013 13:34   doi:10.1186/1471-2288-13-34

Open Data