Kenneth M. Steele wrote:
> In an important sense, all data is grouped-data. We specify
> some boundary conditions of inclusion/exclusion in a unit and
> those conditions typically cover a range of variations which we
> *might* attend to under other circumstances.
>
> To continue with and (likely) mangle Paul's example,
> investigators may be making a mistake by creating intervals of
> 1-5 people, 6-10 people. However, we are still dealing
> with grouped-data when we count "people." We may define a
> person as a living homo sapiens.
I want to object that this is somehow qualitatively different, but I'm
afraid that if I took the time to try to put my objection into words, I'd
discover in the process that Kenneth is completely correct <grin>. So I'll
accept that as just one of those things.
It's most certainly true and obvious if we're talking about the first of my
two examples (age, in which a person 3655 days old claims to be 10 years
old, and so does a person 4000 days old, for example <he writes, fingers
crossed that he did the math right...>). It's much less clearly true in the
case of a person who claims to have 3 children (what would we think of a
mother who volunteered that she has "something more than 2 but fewer than 4
children"?). Perhaps that's not strictly the same thing as having exactly 3
children, but the distinction strikes me as terribly unimportant in this
case. It's certainly not one I'd discuss in a classroom full of sophomores
who are all terrified that passing statistics is going to require them to
master such trivialities...
Paul Smith
Alverno College
Milwaukee
---
You are currently subscribed to tips as: [EMAIL PROTECTED]
To unsubscribe send a blank email to [EMAIL PROTECTED]
