We agree that interpreting the effects of within-group changes in a randomized controlled trial can be problematic. In such trials, outcomes can change over time for reasons unrelated to the intervention. Therefore, drawing conclusions from within-group changes is dangerous. Fortunately, the inclusion of a control group generally overcomes these problems and allows observed differences between groups to be interpreted as the effect of the intervention, regardless of the direction of changes within each of the individual groups.
Hodgson JM, Woodman RJ, Croft KD. Black Tea and Blood Pressure: Did the Blood Pressure Fall or Rise?—Reply. Arch Intern Med. 2012;172(11):894–895. doi:10.1001/archinternmed.2012.1552
Customize your JAMA Network experience by selecting one or more topics from the list below.