Confidence Interval Formula for One Proportion
You'll learn how to construct a confidence interval for a population proportion using the standard formula and the right z-critical value.
The Core Idea
When you estimate a population proportion from a sample (like the percentage of voters favoring a candidate), you want to express your uncertainty. A confidence interval gives you a range of plausible values for the true proportion.
The formula builds on what you already know about the sampling distribution of proportions and their standard error:
CI = p̂ ± z × SE(p̂)*
Where:
- p̂ (p-hat) is your sample proportion
- z* is the z-critical value matching your desired confidence level
- SE(p̂) is the standard error of the proportion: √(p̂(1-p̂)/n)
Choosing the Right z-Critical Value
The z* value depends on your confidence level:
- 90% confidence: z* = 1.645
- 95% confidence: z* = 1.96
- 99% confidence: z* = 2.576
Think of z* as telling you "how many standard errors wide" your interval needs to be to capture the true proportion with your desired confidence.
Putting It Together
If you survey 200 people and 120 support a policy (p̂ = 0.60), and you want a 95% confidence interval:
- Calculate SE(p̂) = √(0.60 × 0.40 / 200) ≈ 0.0346
- Use z* = 1.96 for 95% confidence
- Margin of error = 1.96 × 0.0346 ≈ 0.068
- Interval = 0.60 ± 0.068 = (0.532, 0.668)
You're 95% confident the true proportion lies between 53.2% and 66.8%.
Key Takeaway: The confidence interval for a proportion is p̂ ± z* × SE(p̂), where z* corresponds to your desired confidence level and quantifies how wide the interval needs to be.