FlashKeepers

Statistics for Social Sciences · College

Social Science Stats: Interpreting Social Data

How to read and critique statistics reported in the news, including margin of error and sample size concerns.

30 cards · basic cards · AI-written, checked twice. Edit anything.

Study this set free Look inside first Get FlashKeepers for iPhone
What does margin of error tell you in a news poll?
It shows the range around the reported percentage where the true value likely falls.
How does sample size affect margin of error?
Larger sample sizes produce smaller margins of error.
What is a confidence level in polling?
The probability that the true value falls within the margin of error range, usually 95 percent.
Define correlation as reported in news.
A statistical relationship between two variables; does not prove one causes the other.
What is the key difference between correlation and causation?
Correlation shows two things move together; causation means one directly causes the other.
What is a confounding variable?
A third variable that affects both variables being studied, creating a false appearance of correlation.
Explain what statistically significant means.
A result unlikely to occur by chance alone (usually p less than 0.05), but not necessarily important in practice.
How do leading questions affect survey results?
They bias respondents toward a particular answer by how they are worded.
What is the base rate fallacy?
Ignoring how common something is in the population when interpreting new statistical information.
What does regression to the mean explain?
Extreme measurements tend to be closer to average on a second measurement, not due to treatment effects.
Define p-value in simple terms.
The probability of seeing data this extreme or more extreme if the null hypothesis were true.
What is survivorship bias in statistical reporting?
Only seeing successful cases while overlooking failed ones, creating misleading conclusions.
How can effect size differ from statistical significance?
A result can be statistically significant but have such a small effect size it is not practically important.
What is the Texas sharpshooter fallacy?
Drawing a target around existing data points and then claiming a pattern.
Explain Simpson's paradox.
A trend present in separate groups can reverse when groups are combined.

15 more cards in the app