Unfair comparison

Dissimilar comparison groups

Be careful with intervention comparisons where the comparison groups were too different.

For a comparison of interventions to be fair, the people in the comparison groups should have been as similar as possible at the start of a study. If groups were not similar, this may have affected the results. We cannot know if what happened in the study was due to the groups being dissimilar, the interventions that were compared, or both.

For example, in an intervention comparison, if the group that gets an intervention has better speech or language skills at the beginning of the study than the group who does not get that intervention, that could make the intervention look like it works better than it actually does.

The best way to make sure that the people in both groups are alike is to decide who gets which intervention by chance (randomly) – similar to pulling out names from a hat or flipping a coin.

REMEMBER: Think about whether who got which treatment was decided by chance (randomly) in an intervention comparison, and if the people in the comparison groups were similar at the start of the study.