How would you explain a confidence interval to a non-technical audience?

A confidence interval is a range of values that’s likely to contain the true value of a population parameter. If we repeatedly sample from the population, about 95% of the confidence intervals calculated from those samples will contain the true mean (assuming a 95% confidence level).

For instance, if you want to estimate the average height of men in the US and your sample gives a mean of 70 inches with a 95% confidence interval of [68, 72], then you can say you’re 95% confident that the true average height lies within that range. A narrower confidence interval indicates greater precision and less uncertainty in the estimate.