Resources for teaching LR etc
Significant< Back to search results
XKCD cartoon showing how, if you torture the data enough, they will confess to anything.
- Format Cartoons
- Language/s English
- Target Audience Self-directed learning
- EBM Stage 3 - Appraising evidence
- Duration <5 mins
- Difficulty Introductory
Key Concepts addressed
- 2-3g Statistical significance is not the same as importance
- 2-3e Subgroup analyses may be misleading
If statistical tests are applied repeatedly to treatment outcome measures in different subgroups, one in 20 – on average – will yield a ‘statistically significant’ association <0.05.