Sociology Plus
Confidence Interval Definition
A confidence interval is an interval estimate of a population parameter: a range of values, calculated from sample data, that is likely to contain the true value for the population as a whole. It allows researchers to express, with a stated degree of confidence, how far the population figure may plausibly differ from the one observed in a sample.
Why It Is Needed
Sociologists routinely use samples to learn about whole populations. To gauge how common car theft is across France, one might ask a sample of French people about their experience of it — but a sample’s result will rarely match exactly what a survey of the entire population would show. The confidence interval turns the sample result into a range of estimates for the population.
An Example
A researcher might report 90 per cent confidence that the annual risk of car theft is 8 per cent, plus or minus 2 percentage points. This means the sample was sufficiently large and well selected that there is judged to be only a one-in-ten chance that the population’s true rate differs from the sample’s by more than 2 percentage points.