Monday, September 1, 2008

How reliable are polls?

As of Labor Day, two polls have McCain up by two while another has Obama up by 7.

I was once on Zogby’s site and he has this section where he is asked how a sampling of hundreds to a few thousands can accurately portray what millions and millions of voters say. His response:

“It’s pure probability and statistics. The same theory is involved as when you take a blood test and the clinician draws only a small sample rather than draining all the blood out of your body.”

Considering how different opinions can vary in even the same state, it makes me wonder if this is really an accurate analogy. Makes me think if there was a mathematical formula in probability that was this effective, all the polls would be accurate. Or do the varying polls show that polling isn’t an exact science?

Just asking.

No comments: