Dear all,
As I understand, to perform the Bonferroni correction, we divide the original alpha level (most like set to 0.05) by the number of sub-tests being performed. If let say, I am looking for the association between 3 disease symptoms and 5 genetic polymorphisms using same samples, the p-value of 0.05 should divide by 3 or 5?
Thanks.
It depends on how your tests are set up. See the attached for details
Best wishes, David Booth
It is performed for each of the defined comparisons.
is your design simple, block or factorial?
Thank you very much for the kind explanation. That's very useful. But I am still curious that if we perform whole genome sequencing which will generate more than a thousand data, is the Bonferroni test still applicable? Because the significant value will be very very small and hard to achieve.
- Badges
- Science topic
- Similar topics
- Linguistics
- Composition Studies
- Publication