A range computed from sample data that, under repeated sampling, would contain the true population parameter the stated proportion of the time (e.g., a 95% CI is constructed by a procedure that, applied to many independent samples, produces an interval containing the parameter in 95% of cases). For any single observed interval, the parameter either is or isn't in it — the 95% refers to the procedure's long-run reliability, not to a probability about the specific interval.