"Lloyd" <lparker@emory.edu> wrote in message
news:72b201f1-4031-4404-b4f0-9ae5961c3c68@v13g2000vbb.googlegroups.com...
On Dec 11, 3:36 pm, "Mike Hunter" <mikehunt2@lycos/com> wrote:
> Could they not just continue the statistical MYTHOLOGY they are
> currently
> using? To correct the so called 'below average' thing why not simply
> state
> the PERCENTAGE of failure rate that is actually what the current
> ratings are
> reflecting?
>
> Come to think of it, that would not work. Subscribers would wise up
> and no
> longer subscribe if they realize what CR is showing as a 'list' is
> actually
> showing that ALL manufactures vehicles are falling within the
> standard
> statistical methodology of the 2% failure rate for ALL manufactured
> products
>

> Why don't you READ CR's explanation of their analysis before
> spouting
> off and looking stupid?

http://www.consumerreports.org/cro/c...ity-faq_ov.htm

I have read it and I still believe the little circle over emphasize
small differences, that may not be statistically valid. In the
discussion they talk about the average circle representing a failure
rate of 2.5% (not an actual value, but their example). Do you think
that a sample size of 100 vehicles is enough so that you can cut
things that fine (the difference between average and excellent is 2.5%
and there is "very good in between)? And then consider that the sample
is not a random sample. People choose to participate. And the only
people who have that choice are Consumer Reports readers. So the
people who respond are opinionated, motivated people who like Consumer
Reports. Don't you suppose they are likely to be biased towards
agreeing with CR's editorial opinions?

Ed