Correcting for a Baseline Difference in Group Comparisons on a Binary Outcome: Covariate Adjustment or Analysis of Change?

As a result, the significant group difference at T0‐T1 according to covariate adjustment and at T0‐T2 according to change are no longer significant, although the latter is still close to significance.

also in 2,130 other papers

Comparing between methods per scenario shows the following things: First, covariate adjustment and change from baseline analysis contradict each other with respect to the presence of a group difference on the outcome in all three scenarios where the groups differ at baseline (i.e., scenarios 1, 2, and 4), with one method giving a highly significant group difference, and the other method not even giving a trace of a group effect.

also in 132,142 other papers