Focusing on Key Problems with the Pareto Chart

	Bookmark This Page Email This Page Format for Printing Submit an Article Read More Articles
	Related Tools & Articles The Interrelationship Digraph: Looking for Drivers and Outcomes How To Describe Your Current Business Process How To Describe Your Business Problem
	Discussion Forum "Pretty much every BPMS vendor is going to provide both a modeling and execution environment. You mention Lombardi TeamWorks, and that's a very tightly integrated modeling and execution environment. So is BEA, Savvion, Appian, and pretty much every BPMS vendor..." Contribute to this Discussion

By GOAL/QPC

When entering a business process management initiative for the first time, it's often difficult to figure out just where to start the effort. A Pareto chart is a tool you can use to focus on the problems that offer the greatest potential for improvement by showing their relative frequency or size in a descending bar graph. This article explains the basics.

A Pareto chart is based on the proven Pareto principle, in which 20 percent of the sources cause 80 percent of any problem. It does the following:

• Helps a team to focus on those causes that will have the greatest impact if solved.
• Displays the relative importance of problems in a simple, quickly interpreted, visual format.
• Helps prevent "shifting the problem" where the "solution" removes some causes but worsens others.

A benefit of a Pareto chart is that it measures progress in a highly visible format that provides incentive to push on for more improvement.

How Do You Create a Pareto Chart?

1. Decide which problem you want to know more about.

Example: Consider the case of HOTrep, an internal computer network help line: Why do people call the HOTrep help line? What problems are people having?

2. Choose the causes or problems that will be monitored, compared, and rank ordered by brainstorming or with existing data.

With brainstorming, for example, the group may come up with:

What are typical problems that users ask about on the HOTrep help line?

Based on existing data they may come up with:

What problems in the last month have users called in to the HOTrep help line?

3. Choose the most meaningful unit of measurement such as frequency or cost.

Sometimes you don't know before the study which unit of measurement is best. Be prepared to do both frequency and cost.

Example: For the HOTrep data the most important measure is frequency because the project team can use the information to simplify software, improve documentation or training, or solve bigger system problems.

4. Choose the time period for the study.

Choose a time period that is long enough to represent the situation. Longer studies don't always translate to better information. Look first at volume and variety within the data. Make sure the scheduled time is typical in order to take into account seasonality or even different patterns within a given day or week.

Example: Review HOTrep help line calls for 10 weeks (May 22-August 4).

5. Gather the necessary data on each problem category either by "real time" or reviewing historical data.

Whether data is gathered in "real time" or historically, check sheets are the easiest method for collecting data.

Example: Gathered HOTrep help line calls data based on the review of incident reports (historical).

Tip: Always include with the source data and the final chart the identifiers that indicate the source, location and time period covered.

6. Compare the relative frequency or cost of each problem category.

Figure 1: An example of a problem category count.

7. List the problem categories on the horizontal line and frequencies on the vertical line.

List the categories in descending order from left to right on the horizontal line with bars above each problem category to indicate its frequency or cost. List the unit of measure on the vertical line.

8. An optional step is to draw the cumulative percentage line showing the portion of the total that each problem category represents.

On the vertical line, (opposite the raw data, number, dollars, etc.), record 100% opposite the total number and 50% at the halfway point. Fill in the remaining percentages drawn to scale. Then, starting with the highest problem category, draw a dot or mark an x at the upper right corner of the bar. Add the total of the next problem category to the first and draw a dot above that bar showing both the cumulative number and percentage. Connect the dots and record the remaining cumulative totals until 100 percent is reached.

Figure 2: Add up the entire problem set until 100% is reached.

9. Interpret the results.

Generally, the tallest bars indicate the biggest contributors to the overall problem. Dealing with these problem categories first therefore makes common sense. But, the most frequent or expensive is not always the most important. Always ask: What has the most impact on the goals of our business and customers?

Variations

The Pareto Chart is one of the most widely and creatively used improvement tools. The four variations used most frequently encompass the following:

Major Cause Breakdowns in which the "tallest bar" is broken into subcauses in a second, linked Pareto.

Figure 3: An example of a major cause breakdown.

Before and After in which the "new Pareto" bars are drawn side by side with the original Pareto, showing the effect of a change. It can be drawn as one chart or two separate charts.

Figure 4: An example of a before and after, showing the impact of change.

Change the Source of Data in which data is collected on the same problem but from different departments, locations, equipment, and so on, and shown in side-by-side Pareto Charts.

Figure 5: An example of changing the source of data.

Change Measurement Scale in which the same categories are used but measured differently. Typically "cost" and "frequency" are alternated.

Figure 6: An example showing change measurement scale.

Useful Links

GOAL/QPC
http://www.goalqpc.com/

Buy the The Memory Jogger II:
http://www.bpmenterprise.com/7ht

About the Author: