On Wed, 06 Dec 2006 15:56:20 -0800, SMS <scharf.steven@geemail.com>
wrote in <4577589f$0$82555$742ec2ed@news.sonic.net>:

>I think that it's rather amusing where CR states "our subscribers may
>not be representative of the U.S. population as a whole."

What actually "rather amusing" is how you try to explain away the
admitted bias in CD surveys.

>While true, it
>also makes the CR survey even more valuable, since they're surveying
>people with higher education levels, and higher incomes, that understand
>the differences and why they exist.

There's no evidence of that.

>With such a huge statistical sample,
>there is an extremely small margin or error in the results, less than
>0.5% if the entire population of subscribers in the U.S. (around
>220,000,000) is used. If the 43,000 responses were divided by 20 cities
>equally, this would be 2000 responses per city, the margin of error
>would be less than 2%. No one can argue with these results.

On the contrary -- that's "voodoo statistics", wrong on virtually all
counts.

--
Best regards, FAQ FOR CINGULAR WIRELESS:
John Navas <http://en.wikibooks.org/wiki/Cingular_Wireless_FAQ>