297
It seems to me that Yates correction is used unthinkingly – or perhaps because it sounds like a good idea – but the more I read about it the less convinced I am that it's a good idea at all.
Is anyone prepared to speak up in its defence?
Jean-Benoit Hardouin
Sorry for the defence of the Yates' correction, Ronan, I agree with you.
In the same vein, I don't understand why people continue to perform a test of normality before a Student's test: with small samples, a Mann-Witney tests is more appropriate, and with larges sample, the normality of the variable is not requiered (the central limit theorem allows considering that the means are normally distributed).
But it is hard to overcome these superstitions.
2 votes
1 thanks
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
More Ronán Michael Conroy's questions See All
Similar questions and discussions