How you can use Statistics in the Food Industry - Part 2

Paredo Chart: 

A Paredo Chart is a very simple method of Data analysis that, at its heart which says that is the 80 / 20 rule.  80% of the problems are from 20% of the causes.  Paredo charts can be used in charting events like customer complaints, where there are several types of issues.  The best way to proceed is to first collect the complaints and then organize them from most to least frequent.  Excel can do this task from a complaint list which is summarized in pivot table.  This pivot table can be charted and you can also add a line that tallies the frequency of each complaint.  When you reach 80% of the complaints, you focus on the issues that make-up that amount.

 The above is a quick example of jelly donut issues at a retail store.  The left axis is the number of complaints and the right axis is the cumulative frequency of complaints.  Ordered in this way, it is easy to see "filling squirting out"  is the largest complaint but is this the only complaint to focus on?  The cumulative frequency reaches 80% at "donut crumbled".  So, to correct 80% of the problems we need to solve both the jelly squirting and donut crumbling issues.

As you solve issues, this chart will change and different items will be included in the 80%.  This is a simple, quick, easy, and good way to keep a company focused on which corrective actions to spend time and resources on.


Run Charts:

A run chart plots process data to look for trends and analyze how the long range average is changing.  Below, I created a quick run chart to illustrate this simple method (The Variation of the Weight of Jelly Donuts). The average (mean) calculation for this plot can be found in Excel on the top bar under the formula tab.

The green line represents the mean which is calculated from the weights by the program. You will normally see data points both above and below the mean. As an example: a trend to look for is day 4-6 where the data is steadily rising. If this trend is left to continue it will lead to the weights being "out of spec".

How is this used during production? A blank chart with upper and lower specification limits is used at the start of the production run and the weights are plotted as the QC Tech or Operator weighs each sample. This is not to be confused with the Upper and lower control limits (see histograms in part 1).  The upper and lower specification limits are what you (the company) determine as the limit of acceptable product (based on info such as design of the machine and customer complaints).  With training, the production personnel can learn to look for trends and know when a product is "out of spec". Personally, I look for trends, for example, when three data points are above/below the mean and are approaching the spec limits. This method will give time for the personnel to correct the process before the product goes out of spec. Historical data gathered in this way can be used to help determine when an issue has occurred and how it will be dealt with. For example - a customer complains that the jelly donut dripped on their shirt. If this donut was made on day 15 - then we could say that a 15 gram donut has too much filling.