A confidence interval for parameter θ is an interval [L, U] calculated from sample data such that P(L < θ < U) = confidence level, typically 0.95 or 0.99. For a population mean with known σ, the 95% confidence interval is x̄ ± 1.96(σ/√n). With unknown σ, use x̄ ± t*(s/√n) where t* is the critical value from the t-distribution.