Relative change and absolute benefit
Relative change and absolute benefit
Relative change expresses an effect in proportion to a comparator. An absolute difference expresses how many percentage points separate event risks in comparable people over the same period.
How to read it
Identify the event, comparator, denominator and time frame. Check whether the reported measure is a cumulative risk, an incidence rate or a hazard ratio before interpreting a percentage reduction.
A common pitfall
A 26% reduction does not mean 26 fewer events per 100 people. Do not annualize an absolute difference without support or subtract benefits and harms with different outcomes, populations or observation windows.
Percent and percentage points
Teaching example: a risk of 10% versus 8% over the same fixed period gives a 2-percentage-point absolute reduction and a 20% relative risk reduction. Neither guarantees exactly 2 fewer events in every group of 100.
Why the asundexian percentage uses HR
The 26% figure is 1 minus HR 0.74. HR incorporates event timing; it is not simply the ratio of two final proportions. The global trial reported 6.2% versus 8.4%, approximately 2.2 percentage points apart over its observation period. These are not annual differences or Chinese subgroup proportions.
For clinical decisions, relate the absolute scale to baseline risk, consequences, harms and treatment burden. Statistical significance does not decide that trade-off for an individual.
Practice with a case
Read the Chinese case: Asundexian What does a 26% reduction mean →Read the Chinese case alongside its event counts, observation period, comparator and bleeding uncertainty.
Listen to the Chinese podcast ↗
Read the Chinese case: GLP-1 Why can a rare risk warrant a warning →The Chinese case separates person-time rates in pooled trials, routinely collected data and observational comparisons.
Podcast link not yet supplied.