John Smith wrote:

> How is it of any use to the average Joe?

Err,  what kind of average Joe are we talking about?   I'm not
use how many 'averages' there are but in general one  would talk
about at least three:  The mean, the mode and the median.  Each
are important if you are talking about "Joe" :) depending upon
how you are talking about him. The mean is what is normally mean
by the average.

The mean  is a very useful measure but is can be misleading.  I
can say that the average (mean)  income of the 10 employees in
the ACME widget factory  is $50,000/year which sounds pretty
good.  However it may not sound so good when we suddenly find
that nine employees each make $500/year and the boss makes
$495,500/yr.

How one presents the numbers makes a big difference.  A knowledge
of statistics is very helpful if you want to read and understand
many newspaper articles , watch or listen to the news or
understand many arguments your local municipal government may
make.

Newspapers often make a statement that says something like
'Burglary rate jumps 50% in Podunk".  This does not meant the
same thing if the rate jumps from 2 to 3 than if it jumps from
100 to 150.  If one does not have at least a basic knowledge of
statistics it is difficult or impossible to see if the way the
numbers are being presented makes sense.

Statistics is  just a subset of numeracy which is more and more
important all the time.  The simple ability to look at a couple
of numbers and do even some simple adding or multiplying is very
helpful.

For example: About 20 years ago there was a rash of recovered
memory cases  in children with accusations of Black Masses,
ritual murders etc. all across Canada and the USA.  They  even
seemed to make sense until one suddenly pulled out a calculator
and figures out that some place like New Jersey had  to have ~ 3
million murder victims (and the bodies ) unaccounted for over
about 5 years.  D'uh!  Some ones in New Jersy have managed to
murder over 1% of the the population of the USA and secretly
despose of the bodies?

Stats, at the most basic, simply provides better tools and
concepts to do this.

You might want to have a look at either of the books below:

Best,Joel (2001): Lies, Damned Lies and Statistics:Untangling
Numbers from the  Media, Politicians, and Activists. University
of California Press. ISBN 0-5202-1978-3.

Huff,D (1954): How to lie with statisics. W.W. Norton & Company,
New York.



--
John Kane
The Rideau Lakes, Ontario Canada


.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to