Chris Olsen wrote:
<Snip>
>(1) I would think it highly unlikely that even your poor school districts
>are using textbooks from the circa 1976-1980 period. If (in the incredibly
>unlikely event that a textbook would actually last 20 years) any of your
>schools have such dinosaurs, the occurence of a Tukey box plot on a state
>exam is much less of a problem than your State's textbook adoption plan.
>(2) I would consider it somewhat not unlike unlikely that the high school
>curriclum would conform to Larsen & Marx's Intro to Math stats 2001
>presentation. While IMHO it is an excellent book, I doubt that it should be
>considered a beacon for what a high school curriculum should look like.
>
>(3) My suspicion is that the National Council of Teachers of Mathematics,
>and the NCTM Standards with its strong data analysis and statistics
>component, would force any rational textbook publisher to include the
>so-called Tukey boxplot, and include it median-based, rather than how Dr.
>Tukey could have, might have, or even should have done it.
>(4) High school teachers of mathematics, contrary to your implied
>suggestion, are actually not limited to teaching only whatever appears in
>their textbooks. In point of fact, if one is teaching statistical topics
>intelligently at all, one would be bringing in all sorts of data too new to
>have appeared in any textbook.
<Snip>
For some reason, the NCTS boxplot is not the Tukey boxplot. The NCTS boxplot's
method of handling the whiskers guts one of the key features of the Tukey
boxplot: the ability to flag outliers.
The Mass Dept. of education in their curriculum framework provides an example
of a boxplot taken directly from a K-12 textbook manufacturer's web site. I
consider this improper.
The boxplot shown in Question 39 on the vitally important 2001 MCAS math test
is not a proper Tukey boxplot. The upper outliers are not properly displayed.
If there were an AP stats course, they would probably be using a
college-level text that would be using a true Tukey boxplot, not the
Harcourt-Brace/NCTS boxplot. I don't think it fair for students to know that
the NCTS and the K-12 textbook writers (and the MCAS test writers) have adopted
one feature of the Tukey boxplot, but not the most important feature: the
ability to flag outliers.
Eugene Gallagher
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
