Polling disclaimer A newspaper article that reported the results of an election poll included the following explanation:
The Associated Press poll on the 2012 presidential campaign is based on telephone interviews with 798 randomly selected registered voters from all states except Alaska and Hawaii.
The results were weighted to represent the population by demographic factors such as age, sex, region, and education.
No more than 1 time in 20 should chance variations in the sample cause the results to vary by more than 4 percentage points from the answers that would be obtained if all Americans were polled.
The margin of sampling error is larger for responses of subgroups, such as income categories or those in political parties. There are other sources of potential error in polls, including the wording and order of questions.
a) Did they describe the 5 W’s well?
b) What kind of sampling design could take into account the several demographic factors listed?
c) What was the margin of error of this poll?
d) What was the confidence level?
e) Why is the margin of error larger for subgroups?
f) Which kinds of potential bias did they caution readers about?