Scientific method: Statistical errors
P values, the 'gold standard' of statistical validity, are not as reliable as many scientists assume (Nature 2014)
Popular Posts
Posted by
marina alberti
Global Carbon Dioxide Levels
- Get link
- X
- Other Apps
Interesting article thank you for posting. I think a lack of proper understanding of what the p value actually means is one of the biggest contributors to it being unreliable. Another is violating statistical assumptions e.g. conducting parametric tests on categorical data (I have seen this done often), in such cases there should be very little confidence in outputs of such tests.
ReplyDelete