For lecture on 3 June 2021
When something is statistically significant, it doesn’t always mean that it’s important< Back to search results
- Format Cartoons
- Language/s English
- Target Audience Further education, Self-directed learning
- Duration <5 mins
- Difficulty Introductory
Key Concepts addressed
- 2-3g Statistical significance is not the same as importance
- 2-3f Confidence intervals should be reported
Statistically funny is a blog by Hilda Bastian in which she uses her own cartoons to illustrate key issues in fair tests of treatments.
In this cartoon, entitled “Nervously approaching significance“, Hilda addresses one of the key problems in making sense of research reports. Statistical significance is important to rule out the play of chance in the results of research, but it’s not the whole story.
Use the link to see the full cartoon on Hilda’s blog.
We’re deluged with claims that we should do this, that or the other thing because some study has a “statistically significant” result. But don’t let this particular use of the word “significant” trip you up: when it’s paired with “statistically”, it doesn’t mean it’s necessarily important.
In this cartoon, Hilda reminds us that we can sometimes be blinded by statistics. It’s important to remember that, in looking at the benefits of a treatment, not only do the results have to be statistically significant (i.e. unlikely to have happened if there were no benefit from the treatment), but they must also be important to the patient.
This “clinical significance” is a value judgment, based on a shared understanding between the patient and the carer.