Matching-adjusted indirect comparison of palbociclib versus ribociclib and abemaciclib in hormone receptor-positive/HER2-negative advanced breast cancer
This recently published MAIC is an interesting one. The authors have clearly gone to great lengths to identify and adjust for potential treatment-effect modifiers. However, which baseline characteristics were matched upon was driven, in part, by the need to maintain a "sufficiently large" effective sample size (ESS).
Some might view this as operationally pragmatic, while others might see it as the tail wagging the dog. How should we balance clinically important differences against the need to maintain statistical power/precision?