[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: Tooth Fairy Sample



> Has statistics
> changed over the years, or is this still true?

Bill,

You are not behind the times. For a survey to be performed with as 
little bias as possible, the sample must be "randomly" selected, 
which is a valid subset of the entire population to which the 
statistical correlation is being used to result in a conclusion. If the 
sample is appropriate, there are many methods in which to 
determine the sample size. Again, if done appropriately, the 
Confidence Limits can be very accurate (just look at well-done 
surveys, such as Zogby) where their surveys pretty much reflect 
their sample results.

What you pointed out is similar to other polls taken (yes, even the 
MSNBC poll that has been addressed here lately). It is similar to 
all polls where the results are based on those who log on and 
submit the sample questions. These are not reputable surveys in 
that they reflect the attitudes of those who log on only. The poll is 
not representative of the population at large. The MSNBC poll has 
been accessed by primarily pro-nuclear factions. It doesn't appear 
to coincide with the larger, more appropriate national polls that 
have been taken in the past (as far as percentages that is). AOL 
polls do the same thing, but they do state that this is not a 
scientific survey since it is highly biased by those who take it.
----------------------------------------------------------------------------------
Sandy Perle					Tel:(714) 545-0100 / (800) 548-5100   				    	
Director, Technical				Extension 2306 				     	
ICN Worldwide Dosimetry Division		Fax:(714) 668-3149 	                   		    
ICN Biomedicals, Inc.				E-Mail: sandyfl@earthlink.net 				                           
ICN Plaza, 3300 Hyland Avenue  		E-Mail: sperle@icnpharm.com          	          
Costa Mesa, CA 92626

Personal Website:  http://www.geocities.com/capecanaveral/1205
ICN Worldwide Dosimetry Website: http://www.dosimetry.com
************************************************************************
The RADSAFE Frequently Asked Questions list, archives and subscription
information can be accessed at http://www.ehs.uiuc.edu/~rad/radsafe.html