Bias? Political analyst Michael Barone has written that conservatives are more likely than others to refuse to respond to polls, particularly those polls taken by media outlets that conservatives consider biased (The Weekly Standard, March 10, 1997). The Pew Research Foundation tested this assertion by asking the same questions in a national survey run by standard methods and in a more rigorous survey that was a true SRS with careful followup to encourage participation. The response rate in the standard survey was 42%. The response rate in the rigorous survey was 71%.
a) What kind of bias does Barone claim may exist in polls?
b) What is the population for these surveys?
c) On the question of political position, the Pew researchers report the following table:
|
|
Standard Survey
|
Rigorous Survey
|
|
Conservative
|
37%
|
35%
|
|
Moderate
|
40%
|
41%
|
|
Liberal
|
19%
|
20%
|
What makes you think these results are incomplete?
d) The Pew researchers report that differences between opinions expressed on the two surveys were not statistically significant. Explain what statistically significant means in this context.