Skip to main content

Table 5 Multivariable linear regression of difference between ITT lower CI and PP lower CI on study characteristics and risk for bias

From: Intention-to-treat analysis may be more conservative than per protocol analysis in antibiotic non-inferiority trials: a systematic review

Predictors Co-efficient (95% CI) P-value
PP exclusion based on concomitant therapy −0.81 (− 1.93 to 0.31) 0.1558
Low risk for allocation concealment bias −0.74 (− 1.82 to 0.35) 0.1810
Low risk for performance bias −1.35 (− 2.94 to 0.24) 0.0960
Low risk for detection bias 0.70 (−0.97 to 2.37) 0.4076
Proportion of treatment arm in the ITT population that was included in the PP population per every 10% 2.89 (2.13 to 3.65) < 0.0001
Proportion of control arm in the ITT population that was included in the PP population per every 10% −2.73 (−3.37 to − 2.09) < 0.0001
  1. The dependent variable in the model is ITT lower CI limit minus PP lower CI limit. Therefore, a negative co-efficient is associated with a smaller ITT lower CI limit, so the ITT analysis is more conservative than PP analysis. Conversely, a positive co-efficient is associated with a smaller PP lower CI limit, so the PP analysis is more conservative than the ITT analysis
  2. CI Confidence interval, ITT Intention-to-treat, PP Per-protocol