Basic statistics for clinicians: 3. Assessing the effects of treatment: measures of association
Assessing the effects of treatment: measures of association.Key Concepts addressed:
- 1-3 Association is not the same as causation
- 2-16 Confidence intervals should be reported
- 2-17 Don’t confuse “statistical significance” with “importance”
In the third of a series of four articles the authors show the calculation of measures of association and discuss their usefulness in clinical decision making. From the rates of death or other “events’ in experimental and control groups in a clinical trial, we can calculate the relative risk (RR) of the event after the experimental treatment, expressed as a percentage of the risk without such treatment. The absolute risk reduction (ARR) is the difference in the risk of an event between the groups. The relative risk reduction is the percentage of the baseline risk (the risk of an event in the control patients) removed as a result of therapy. The odds ratio (OR), which is the measure of choice in case-control studies, gives the ratio of the odds of an event in the experimental group to those in the control group. The OR and the RR provide limited information in reporting the results of prospective trials because they do not reflect changes in the baseline risk. The ARR and the number needed to treat, which tells the clinician how many patients need to be treated to prevent one event, reflect both the baseline risk and the relative risk reduction. If the timing of events is important – to determine whether treatment extends life, for example – survival curves are used to show when events occur over time.