Example of Analysis of Means for Poisson data

A manager at a food packing company wants to monitor the number of overfilled containers for each of the packing machines. The manager counts the number of overfilled containers per machine on the same day.

To determine whether some machines overfill at different rates than other machines, the manager uses analysis of means for Poisson data.

  1. Open the sample data, Packing.MTW.
  2. Choose Stat > ANOVA > Analysis of Means.
  3. In Response, enter Overfilled.
  4. Under Distribution of Data, select Poisson.
  5. Click OK.

Interpret the results

In this plot, the 11th machine has an overfill count of 0, which is unusually small. The 14th machine has an overfill count of 13, which is unusually large. The manager schedules diagnostic work for the 14th machine to rule out any mechanical problems.

By using this site you agree to the use of cookies for analytics and personalized content.  Read our policy