On Apr 3, 2:04=A0pm, Richard Ulrich <Rich.Ulr...@[EMAIL PROTECTED]
> wrote:
Thanks for your comments, Rich.
> The proper drawing will truncate each whisker at
> a point where there is still data, and will show
> points that may exist beyond the range.
>
> So if there is much skewness, there will be
> whiskers of different lengths
But that's not _necessarily_ true, is it?
The pre-truncation whisker length depends
only on the data between q1 & q3, whereas
whisker truncation itself depends only on the
data outside these values. So, depending
on the ranges of values below q1 and
above q3, you might not truncate either
whisker, even with quite large skewness.
I can see how your comments would be true
with lots of distributions, though.
|
