A computed 95% confidence interval does cover the true value with probability 0.95 if epistemically interpreted

Abstract

Suppose the lifetime of a large sample of batteries in routine use is measured. A confidence interval is computed to 394 plus/minus 1.96 times 4.6 days. The standard interpretation is that if we repeatedly draw samples and compute confidence intervals, about 95% of the intervals will cover the unknown true lifetime. What can be said about the particular interval 394 plus/minus 1.96 times 4.6 has not been clear. We clarify this by using an epistemic interpretation of probability. The conclusion is that a realised (computed) confidence interval covers the parameter with the probability given by the confidence level is a valid statement, unless there are relevant and recognisable subsets of the sample.