Hi,
I've been teaching an introductory stats course for several years.
I always learn something from my students...hope they learn too.
One thing I've learned is that confidence intervals are very tough
for them. They can compute them, but why?
Of course, we talk about confidence interval construction and I try
to explain the usual "95% of all intervals so constructed will in the
long run include the parameter...blah, blah". I've looked at the
Bayesian interpretation also but find this a bit hard for beginning
students.
So, what is your best way to explain a CI? How do you explain it
without using some esoteric discussion of probability?
Now, here's another question. If I roll 2 dice and
find the mean of the pips on the upturned faces. You can compute
sample standard deviations, but if you roll 2 alike the s.d. is 0.
So, you cannot compute a CI based on these samples. How would
you explain?
Thanks,
Warren
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
