In clinical trials, the clinical significance (“treatment effects”) is how well a treatment is working. For example, a drug might be said to have a high clinical significance if it is having a positive, measurable effect on a person’s daily activities.
Common measures of clinical significance include relative risk, absolute risk, and number needed to treat (NNT).
Clinical Significance vs. Statistical Significance
Clinical significance is sometimes called clinical importance, to differentiate it from statistical significance.
- Statistical significance is associated with p-values and other repeatable, measurable statistics. Specifically, it tells you how likely any differences in outcomes between the treatment group and control groups are not due to chance alone.
- Clinical importance/significance is more of a set of clinical observations about how well a particular treatment is performing. It is a measure of how big the differences in treatment effects are in real-world practice.
Clinical significance and statistical significance are often combined to provide a more well-rounded measure of treatment success or failure. For example, relative risk can be reported along with a 95% confidence interval.
Statistical significance, while a very important part of randomized trials, tells you nothing about the clinical importance of any treatment. In addition, null hypothesis testing and the associated p-values are often misinterpreted. While clinical importance is easier to understand and interpret (the importance is often reported in easy to understand language), there are no specific guidelines on where the boundary is between “important” and “not important”. It’s up to the researchers to define where this boundary lies, and that subjective boundary is heavily prone to bias. Caution should be taken when interpreting clinical significance to ensure that the findings are reasonable.
Leung, W. Balancing statistical and clinical significance in evaluating treatment effects.
Shober, P. et al. (2018) Statistical Significance Versus Clinical Importance of Observed Effect Sizes: What Do P Values and Confidence Intervals Really Represent? Anesthesia & Analgesia: Volume 126 – Issue 3 – p 1068-1072
Virginia Tech image: Retrieved Sep 3, 2019 from: http://www.ari.vt.edu/research_area/risk/
Stephanie Glen. "Clinical Significance" From StatisticsHowTo.com: Elementary Statistics for the rest of us! https://www.statisticshowto.com/clinical-significance/
Need help with a homework or test question? With Chegg Study, you can get step-by-step solutions to your questions from an expert in the field. Your first 30 minutes with a Chegg tutor is free!
Comments? Need to post a correction? Please post a comment on our Facebook page.