Use ANOM with Poisson data to identify unusual observations. It tests the hypothesis that all the observations come from the same Poisson distribution at the a-level you specify.

The ANOM plot for Poisson data consists of the following:

·    The number of defects for each sample.

·    Center line (green) – the mean number of defects.

·    Lower and upper decision limits – used to test the hypothesis. Minitab looks for values located beyond the decision limits and marks them with a red symbol.

-    If a sample value is located beyond a decision limit, you can reject the hypothesis that the value is equal to the mean.

-    If a sample value falls within the decision limits, you cannot reject the hypothesis that the value is equal to the mean.

For the packing data, Minitab identifies machine 11 as having an unusually small overfill count (0). Therefore, machine 11 is working effectively because you want machines to have low overfill counts.

Minitab identifies machine 14 as having an unusually large overfill count (13), suggesting that you should inspect this machine.