An asterisk appears in place of a p-value for the 3-parameter lognormal, 3-parameter gamma, and 3-parameter loglogistic distributions. The asterisk indicates that Minitab cannot calculate a p-value for that distribution.
To interpret the goodness-of-fit test results:
1. Look only at the basic distributions first (do not consider distributions with threshold parameters, like the 2-parameter exponential or 3-parameter lognormal).
2. Find the distributions that have the highest p-values. If none of the distributions have p-values greater than your alpha value (0.05), then none of the distributions adequately fit your data.
3. Consider the 2-parameter and 3-parameter variations of the distributions that appear to be adequate.
The Likelihood Ratio Test (LRT P)
When you fit with a 3-parameter distribution, you want to know if the improvement from a 2-parameter distribution is significant. If the p-value is less than alpha, then the improvement by using a 3-parameter distribution (instead of a 2-parameter distribution) is large enough to be statistically significant.
