 bignosemousie says: How will polling adapt to this trend? Can we trust any statistics, even with the margin for error? Polling institutions have been dealing with this issue for a while. Instead of using directories, they use Random Digit Dialing (RDD) to generate phone numbers from scratch to hit unlisted numbers in a systematic manner. From Gallup's 1997 FAQ: It's important to go through this complicated procedure because estimates are that about 30% of American residential phones are unlisted. Although it would be a lot simpler if we used phone books to obtain all listed phone numbers in America and sampled from them (much as you would if you simply took every 38th number from your local phone book), we would miss out on unlisted phone numbers, and introduce a possible bias into the sample. I'm unlisted and I know my views aren't represented. haha. Actually, I believe that only the last four digits of phone numbers are generated from scatch. Pollsters know the valid area codes and exchanges beforehand. I think the problem is that pollsters don't have a good listing of valid exchanges used by cell phone companies. Here is a pollster's rundown on the cell phone problem. He explains why pollsters don't call cell phones (answer= for legal reasons) and his take is that as of now, the cell phone-only population is not a huge problem, but as this group gets larger that won't be true. |
View the Top Clips from July 5, 2007
Embed This Clip In Your Site...
|
||||||||||||
|
|
|||||||||||||
|
New from the makers of Clipmarks: Amplify.com - Don't just share the news...Amplify it!
|
|||||||||||||
