U.S. Government and Civics / Unit 10: Public Opinion, Media and Civic Participation
10.2 Measuring Public Opinion
Notes
Public opinion is what the population thinks about issues and leaders. Polls measure it.
- A random sample gives everyone in the population an equal chance of being chosen, so a sample of about 1,000 people can represent the nation.
- Margin of error (sampling error) shows how much a result may differ from the true value. With about 1,000 people, it is about $\pm 3$ percentage points.
- Example: a poll shows 52% for a measure with a margin of error of $\pm 3$. True support is likely between 49% and 55%, so the race is too close to call.
- Bias can come from unrepresentative samples, leading or confusing question wording and question order.
- Exit polls survey voters as they leave polling places. Tracking polls follow opinion over time.
- A push poll is not real research; it uses loaded questions to spread negative information about a candidate.
Practice
A poll finds 48% support for a candidate with a margin of error of $\pm 4$ points. Her true support is most likely between:
$48 - 4 = 44$ and $48 + 4 = 52$.
A pollster surveys only people who visit a sports website. The main problem is:
Website visitors are not a random sample of the population.
"Would you support Candidate X if you knew she voted to raise taxes on struggling families?" This question is an example of:
Loaded wording is used to persuade, not to measure opinion.
Ready for more? Take the Unit 10 test.