In conclusion, ANCOVA should be the analysis of choice, a priori, for RCTs with a single post-treatment outcome measure previously measured at baseline; its superiority is particularly marked when baseline imbalance is present, but also – in terms of precision – when groups are balanced at baseline.
Both self-reported left-hand preference and left-hand superiority in baseline typing were associated with reduced interference on the cognitive task, and the reduced interference in those groups seemed to reflect relatively loose coupling between manual and cognitive tasks.
In conclusion, this analysis confirms the favourable benefit/risk of first-line nab-PC treatment in older population (patients aged ⩾60 or ⩾70 years) with good baseline performance status, including superiority in terms of OS, QoL, safety/toxicity, and Q-TWiST.
In all RCTs, both the APM and physical therapy groups showed clinical improvements from baseline to follow-up, although superiority of APM compared with physical therapy could not be demonstrated at any time point.
Amitriptyline, duloxetine, and pregabalin reduced BPI severity, BPI interference, and visual analog scale pain when compared with placebo baseline, with no one treatment showing superiority to another (Table 2).
This discrepancy may be due to small and unequal sample size numbers in the two subgroups (24 vs. 12 patients), or to differences between the groups already at baseline, or may indeed reflect a non-superiority of the combination therapy.
Mean HbA1c changes from baseline to primary endpoint are reported to show superiority of dulaglutide over insulin glargine (mean dose not reported) (P<0.001).
The primary efficacy variable, change in HbA1c from baseline at the study endpoint, was analysed for superiority of vildagliptin 50 mg bid over voglibose 0.2 mg tid.
After adjustment for baseline pain score, however, duloxetine showed evidence of superiority to both tramadol and hydromorphone, but not for the other treatments, including etoricoxib.
This study is a six-week, two-arm, parallel, randomized controlled trial (two weeks baseline and four weeks intervention; Figure 2) with a superiority design.
The primary efficacy end point was the change from baseline to week 12 in HbA1c to determine the superiority of linagliptin over placebo.
