In addition, the double-blind, double-dummy design may have prevented the detection of differences between both treatment arms regarding discontinuation rates.
A multilevel modeling approach will be conducted to evaluate differences between the intervention group and both control arms regarding the development of primary and all secondary outcomes during the study period.
There was no significant difference between treatment arms regarding protocol violations related to intravascular volume expansion (see Additional file 5).
It was not possible to reevaluate outcomes based on presenting ulcer size, but based on the similarities between study arms regarding ulcer size in the five studies that mentioned it, such an assessment was not necessary.
Comparisons between treatment arms regarding proportion of patients achieving HIV-1 RNA <200 copies/mL and <50 copies/mL were made using the Cochran-Mantel-Haenszel test controlling for prior antiretroviral drug experience.
It was suggested that utilisation of a composite definition of progression based on both RECIST and CA-125 criteria (instead of only one or the other) would increase the statistical power for tests of differences between trial arms regarding progression-free survival (PFS) (Rustin et al, 2006).
Mixed models repeated measures analysis revealed significant differences between the study arms regarding total PANSS score change favouring n-3 PUFA (p = 0.016; effect size (ES) = 0.29).
Indeed, even in trials with large sample sizes, there will usually be an imbalance between arms regarding baseline utility score.
Of note, OS was a secondary endpoint, and there were imbalances between arms regarding second-line therapy and surgery to remove liver metastases.
There were no significant differences between the two arms regarding CR rate (49 vs 43% P=0.613) and day +100 OS (44 vs 39% P=0.619).
