On 19 Dec 2018, at 4:42, 'John Clements' via users-redirect wrote:
I often find myself wanting to use a t-test. Wikipedia suggests that
really, I should probably be using Welch’s t-test, because it works
well when variances and sample sizes are different, and about as well
as student’s t-test when variances and sample sizes are the same.
My vague recollection is that wanting these things makes me a
frequentist, and a Bad Person. And that this is related to the reason
that it’s not already present in the math/statistics package, whose
feet I am (seriously!) not fit to wash. Not in a statistical sense,
any way.
Are there good reasons not to implement a simple package containing
welch’s t-test? And maybe student’s t-test, just for the heck of
it?
Why not extend math/statistics with both t-tests (welch-t-test,
student-t-test)? I'm sure Neil would welcome it.
Jesse
PS Frequentists are alright by me.
--
You received this message because you are subscribed to the Google Groups "Racket
Users" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to racket-users+unsubscr...@googlegroups.com.
For more options, visit https://groups.google.com/d/optout.
