Use Anderson-Darling statistics to compare how well different distributions fit your data. The Anderson-Darling statistic measures the area between the fitted line (based on chosen distribution) and the nonparametric step function (based on the plot points). Precisely, the Anderson-Darling statistic is a squared distance that is more heavily weighted in the tails of the distribution.

Smaller Anderson-Darling values indicate that the distribution fits the data better.

If you use the alternative estimation method, the least squares (LSXY) method, Minitab calculates a Pearson correlation coefficient in addition to the Anderson-Darling statistic. The correlation coefficient is a positive number that can be no larger than 1. Higher correlation coefficients indicate that the distribution provides a better fit to the data.

Use the Anderson-Darling and Pearson correlation coefficient as relative, as opposed to absolute, measures of fit by comparing the values from several distributions.