A confidence interval is a range of plausible values for an unknown population parameter, such as a mean or proportion. A confidence level tells how reliable the method is over many repeated samples, such as 95% or 99%. These ideas matter because statistics usually works with samples, not entire populations.
The goal is to estimate an unknown true value while clearly showing the uncertainty in that estimate.
For one sample, you calculate one confidence interval, and that interval either contains the true population value or it does not. The confidence level does not say there is a 95% chance that this one fixed interval contains the fixed true value. Instead, it means that if the same sampling method were repeated many times, about 95% of the intervals would capture the true value.
Higher confidence levels require wider intervals because the method must be more likely to include the true value.
Key Facts
- Confidence interval = sample estimate ± margin of error
- Margin of error = critical value × standard error
- For a mean with known sigma: CI = x̄ ± z* × sigma/sqrt(n)
- For a proportion: CI = p̂ ± z* × sqrt(p̂(1 - p̂)/n)
- A 95% confidence level means about 95% of intervals from repeated samples capture the true parameter.
- Increasing the confidence level increases the critical value and makes the interval wider.
Vocabulary
- Confidence level
- The long-run percentage of confidence intervals that would contain the true population parameter if the sampling process were repeated many times.
- Confidence interval
- A range calculated from sample data that is used to estimate a population parameter.
- Population parameter
- A fixed but usually unknown numerical value that describes a population, such as a population mean or proportion.
- Sample estimate
- A statistic calculated from sample data that is used as the center of a confidence interval.
- Margin of error
- The amount added to and subtracted from a sample estimate to form a confidence interval.
Common Mistakes to Avoid
- Saying there is a 95% chance the true value is inside this specific interval is wrong because the true parameter is fixed and the interval has already been calculated.
- Confusing confidence level with confidence interval is wrong because the level describes the long-run method, while the interval is one range from one sample.
- Thinking a higher confidence level makes the estimate more precise is wrong because higher confidence usually creates a wider interval.
- Ignoring sample size is wrong because larger samples reduce standard error and usually make confidence intervals narrower.
Practice Questions
- 1 A sample mean is 52, the standard error is 3, and the critical value for a 95% confidence interval is 1.96. Calculate the 95% confidence interval.
- 2 A poll finds p̂ = 0.60 from n = 400 people. Using z* = 1.96, calculate the approximate 95% confidence interval for the population proportion.
- 3 Two confidence intervals are made from the same sample data: one at 90% confidence and one at 99% confidence. Which interval should be wider, and why?