Not So Normal Capability Analysis (#51)

When collecting data for a transactional/service process, most of the time the allocation of the data is considered “non-normal.” This data is usually lead-time data.
Let’s look at an example. One of our clients asked us to complete a Lean Six Sigma project onsite. Our aim is to trim the lead-time it takes to set up an IT application. The original lead time for installing an IT application should take 30 days or less to install, test, and certify; if the team works 10 hour days, Monday through Friday. Following the standard process; the goal “lead time” needs to be at or around 24 days.
Though our goal of a 24 day lead time is less than the original 30 day lead time, the client’s customers have stated that they would be better satisfied if the IT application was installed in a shorter amount of time.
To meet the customer’s demand, our team needs to comprehend what our capability baseline is. To do so, we should complete a Capability Analysis.
Because the collected data is in a “non-normal” distribution, the graph should look positively skewed like a ski slope. Refer to image below:

In this blog you will learn 5 steps that will help you understand Non-Normal Process Capability that helps you meet Customer demands.

1.       Gather Data
a.       Record data from your process. From our example above, we know that we need to collect sample data. Our team should collect 100 samples which will show the complete variation spectrum that typically occurs within the process.
b.       In our example, the complete variation spectrum is coming from 3 Installation Teams. We should gather a minimum of 30 data points from each installation team. To download the collected data into a Microsoft Excel Sheet Click Here.
2.       Classify Distribution Shape
a.       From our data collection, we recognize that it will represent a Non-Normal Distribution. Now we have to confirm our presumption with data. To do so we need to administer a Normality Test to prove our data is not normal.
b.       Refer to the Non-Normal-Data Excel Spreadsheet for this example. We will use Minitab 17 to perform the statistical analysis. Copy and paste the Lead Time data (found in the Excel Spreadsheet) to Minitab. To do the Normality Test click Stat then Basic Statistics then Normality Test. Fill in your Variable with the Lead Time data and select OK. Refer to image below.


Below is a snapshot of what your Probability Plot should look like.

Our P-Value, represented by the red outline, is <0 .05="" 95="" a="" accept="" can="" collected="" confidence="" data="" distribution.="" fit="" into="" level="" non-normal="" o:p="" our="" so="" that="" we="" will="" with="">
3.       Validate Stability
a.       In a Lean Six Sigma project, your DMAIC Roadmap will guide you to the correct solution to your problem. One of the things we teach in class is for our students to be on the lookout for indicators during the project.
b.       For this example, these indicators derive from an imbalance in our process. These indicators are represented by red dots. To prove consistency, we need to perform an ImR Chart. To do so click Stat then Control Charts then Variables Chart for Individuals then ImR. Fill in your Variables with Lead Time. Refer to image below.


Your result should look like this:

The image above displays two indicators, as you can see by the red dots, on both charts. The red dots display aberrant variation. This is the first place your team needs to look to discover the cause. These indicators are a potential sign into the problem your project is trying to solve. When you classify and fix these indicators, you can add in more data points or simply get rid of these points in the data group. For this example we are going to allow these points to remain in the data set.

4.       What is the best fit shape for your Non-Normal data.
a.       You have quite a few options for Non-Normal Data distributions so to find the best fit we will use the “Individual Distribution Identification” tool in Minitab. To find click Stat then Quality Tools then Individual Distribution Identification. Fill in the Single Column and Subgroup Size as reflected in the image below.


This should result in four different graphs; each of which should include four different distributions.








You need to select the Distribution that has the Biggest P-Value (aside from the Johnson and Box Cox Transformation). For this example, our best fit is “Exponential” Distribution.

5.       Define Process Capability
a.       Since we have found our Best Fit for the data, it is time to perform the Non-Normal Capability Analysis. To do so click Stat then Quality Tools then Capability Analysis then Non Normal. Fill in the Capability Analysis/ Non Normal Distribution as reflected in the image below. Check that you have selected the “Exponential” box in the Fit Distribution. Select Options.



Complete the Options box as shown below:


For our example it would be more realistic to select Percents under Display; simply because it would take several years for the company to have an output (Installation time for each I.T. Team) over one million. Select OK then select OK again. Your Process Capability Report should look like the image below.




You can depict the conclusion of the Non-Normal Capability Analysis testing the same way you would with normal data. Capability is found by comparing Process Variation Width (VOP) to Specification Width (VOC). It is ideal for your process spread to be less than and in between the specification spread. Our data is not like this. The Overall Capability Box represents how your process performs in relation to the specification limits. Compare Ppk with the indices minimum requirement to determine whether or not your process is capable. For most, 1.33 is the minimum requirement for a Capable Process and anything less than 1 is thought to be inadmissible.

Our example has a Ppk of 0.23. This means that the Installation Teams need to make improvements within their process to be able to meet Customer Requirements. Completing each step shows us how much we can improve our process and where.

About Six Sigma Development Solutions, Inc.
We are Certified as an Accredited Training Organization with the International Association of Six Sigma Certification (IASSC)
“The IASSC Accredited Training Organization (ATO) designation validates Six Sigma Development Solutions, Inc. has demonstrated adequate management systems, courseware with a high degree of correlation to the subject matter contained in the IASSC Bodies of Knowledge, delivery schema consistent with such content and highly qualified instructors.”
We Provide Public Lean Six Sigma Green Belt and Lean Six Sigma Black Belt Certification Training Courses in 34 Cities across the globe.
Our Training Centers are located in: Albuquerque, New Mexico | Anchorage, Alaska | Atlanta, Georgia | Austin, Texas | Boston, Massachusetts | Calgary, Canada | Charlotte, North Carolina | Chicago, Illinois | Cincinnati, Ohio | Cleveland, Ohio | Columbus, Ohio | Dallas, Texas | Denver, Colorado | Detroit, Michigan | Dubai, UAE | El Paso, Texas | Fort Smith, Arkansas | Honolulu, Hawaii | Houston, Texas | Indianapolis, Indiana | Jacksonville, Florida | Kansas City, Missouri | Las Vegas, Nevada | London, England | Los Angeles, California | Louisville, Kentucky | Memphis, Tennessee | Mexico City, Mexico | Milwaukee, Wisconsin | Minneapolis, Minnesota | Montreal, Canada | Nashville, Tennessee | New Orleans, Louisiana | New York City, New York | Northwest Arkansas | Orlando, Florida | Philadelphia, Pennsylvania | Phoenix, Arizona | Pittsburgh, Pennsylvania | Portland, Oregon | Raleigh, North Carolina | Salt Lake City, Utah | San Diego, California | Seattle, Washington | St. Louis, Missouri | Tampa, Florida | Toronto, Canada | Vancouver, Canada | Washington, DC

We Provide Onsite Lean Six Sigma Certification Training. Some of the training's we provide are: Lean Six Sigma Black Belt, Lean Six Sigma Green Belt, Lean Six Sigma Yellow Belt, Lean Six Sigma Champions Training and Lean Certifications for Healthcare, Finance, I.T, Manufacturing, Processing, Logistics, Retail Sales and Government.
SSDSI will come to your site to train for your choice of the Lean Six Sigma Certification Levels. Onsite training is more cost effective than open enrollment training when training larger groups of team members.
Benefits of Onsite Training:
The Training is focused on Your Opportunities
SSDSI uses your opportunities in class (vs. generic examples)
You will get the experience of a seasoned Lean and Six Sigma Master Black Belt who will help mentor you while completing your Lean and Six Sigma Project
You can train up to 20 employees for one fixed cost (this cost includes course ware and the instructors travel & lodging)
Our courses are full of games, simulations, and active learning to help the adult learner
SSDSI can customize the training to meet your company’s particular training needs
Call Kevin Clay at 214-731-3176 or email at kclay@sixsigmadsi.com for more information

Comments

Post a Comment

Popular posts from this blog

McDonald's and the an example of a Lean Pull process...

When I was 18 we (my family and I) had just returned on an accompanied tour with my father (a U.S. Marine) in London, England. We were in Jacksonville, NC for around two weeks when he received orders to ship off to the middle east to be a part of "Desert Storm". I was preparing to go to college in Greenville, NC which was about three hours from Jacksonville. I changed my plans when we got the news that my father was to be deployed again. I decided to go to the local community college so that I could watch after my mom and two sisters.  My first order of business once I was registered for school was to find a job. The only employment I found that would work around my schedule was McDonalds. I was hired as a night shift cook. I have always had the mind to be frugal with money. Like teaching, you don't enlist in the Marine Corps to get rich. I say this because I immediately saw waste at the McDonalds though At the time I did not know the concepts of Lean nor Six Sigma. ...
Read more

We Invest  in process improvement like we invest in our health...

I'm sure most of you have seen thousands of infomercials over the years of "get fit quick" gimmicks. The man on the TV that I call "the Circus Barker" that excitedly tells you of a way to lose weight and get fit in seven days. We fall for these gimmicks time after time with the same result ... a new contraption that sits in a closet or in the middle of the room as a clothes hanger. Why does this happen? Because we want the quick fix with minimal investment.  Let's correlate the above example with an organizations investment in process improvement. When I am asked by people "Kevin, what do you do?"... I answer "I am like a fitness trainer for your organization except that I focus on the health of  your processes not necessarily the people." Organizations investing in process improvement are investing in the health of their company. For those of you that have significantly improved your health and sustained that improvement know that t...
Read more

Myth Busters (#77)

Image
Myth Busters! I love watching the show Myth Busters! It’s entertaining and enlightening; hopefully you think these blogs are too!  😊 The Lean Six Sigma Methodology is full of myths. One of these being that it is the CI’s role to improve processes. Saying it louder for those in the back: It is a Myth that the CI’s role is to Improve Processes. Confused? Let me explain. A myth is a false idea or belief that is widely recognized. Most people believe that it is the CI’s responsibility to improve processes. Why wouldn’t you believe that? Their title literally means Continuous Improvement. Let’s take a look at this example of how the majority of companies practice process improvement. Charlie is a Continuous Improvement Engineer for the Operating Expense Dept in his organization. Their team consists of three people out of a staff of 900. Leadership has asked the team to speed up the order entry process; a request made by corporate because they believe that the order entry...
Read more