A tolerance interval contains at least a specified proportion of the population. It is a confidence interval for a specified proportion of the population, not the mean, or standard deviation. Complete discussions of tolerance intervals are found in Meeker et al. (2017) and in Tamhane and Dunlop (2000).
When you select the Tolerance Interval option for a variable, the Tolerance Intervals window appears. Use the window to specify the confidence level, the proportion to cover, a one-sided or two-sided limit, and the method. The two available methods are Assume Normal Distribution and Nonparametric. The Assume Normal Distribution option computes tolerance intervals that are based on the assumption that the sample was randomly selected from a normal distribution. The Nonparametric option computes distribution-free tolerance intervals.