Misleading outcomes

Relative effects

Look out for treatment effects that are described as relative effects.

Relative effects (ratios) alone don’t provide enough information for judging the importance of the difference between the two groups. They also may give the impression that a difference is more important than it actually is.

For example, if an intervention cuts the likelihood of a child having a persistent stammer in half and the baseline risk of persistence is 2 in 100, giving the intervention may be worthwhile, even if it also has a mild negative impact (such as a child becoming more self-conscious). If, however, the risk of persistent stammering is 2 in 10,000, then giving the intervention may not be worthwhile even though the relative effect is the same. The absolute effect of a treatment (the difference) is likely to vary for people at different baseline risk.

REMEMBER: Don’t be tricked by relative effects. Always consider the absolute effects of treatments.