In metrics the most honest finding will be that your metrics will have degrees of variation. Understanding where and how those metrics occur, is the key to using your data in a forward thinking strategy. Let’s start with something simple, like toy production. We are going to track some standard variation sources.
Within Unit Encoding
This variation source occurs when you are measuring output from a single production cycle. Some places that variation is likely to occur are the width of parts, color shading, length of toy etc. Now you can choose to analyze different production cycles on the same day or alternating days, but you will always be comparing samples from the same cycle. A new production sample means a new data point.
Between Unit Encoding
These names are dead giveaways, but I digress! This implies that you are looking at samples from two different production cycles. This is different in that you would want to identify two different samples from different production cycles. The variations you are looking for will give you some clue as to whether the variations are operation influenced or process influenced.
This is the trickiest variation source. This specifically calls for you to compare your variation averages from all of your data points in a single day. So you can theoretically have both within unit variation data and between unit variations data, depending on how specific you need to get.
The key to getting the most out of your data is to understand what it’s telling you. Understanding where the variations are coming from is the first step to getting the most out of your data.
We opened last week with Process Capability and before we go full-fledged into that area, I want to pause and put some focus on capability studies.
What is a Capability Study?
To review from last week, a capability study is a way to ensure that your process is consistent over an extended period of time. For example if step 3 in your process produces 3 errors per cycle for 3 years, your process in consistent.
How Do You Find Stability?
There are a ton of tools you can use to test the stability of your process, but some of the most common tools are Time Series Plots and Control Charts. In addition to these tools there is a step by step process (of course!) to test the capability of your process, here they are.
What should know about capability studies?
As with all 6Sigma tools, the effectiveness of this tools lies more in how you understand and how you apply it. The most important things to remember are:
- Capability studies are used to measure the same parts of the process, at the same stage in the process at exactly the same time every time it is measured.
- You can use the capability study on discrete and continuous data.
- You get the best (ie most meaningful) information when you run the study on already stable and predictable data. New processes are not the best place for this tool.
- When you hear Sigma Level, they are talking about capability.
- Capability studies require you to understand:
- The limits of your customer or organization.
- The difference between short-term and long-term
data and what those differences mean to your organization or customer.
- Mean and standard deviation.
- How to assess normality of your data.
- How your organization or customer determine Sigma level.
Capability Studies can give you a great deal of insight on how your organization is running and what is making it difficult. This is one way to get a sense of the information flow and the quality of the information you can get your hands on. So let’s start off the new year with a look at what your data is telling you. Happy Hunting!
Everything we measure generates variation, especially when there are multiple hands involved. To be honest even with just one person performing the same function, there will be some variation. Variation is not the enemy, uncontrolled variation is our nemesis!
When creating a Measurement System Analysis (MSA) there are 3 characteristics that you should focus on before you try any of the bells and whistles.
Is it accurate?
You need to know how accurate your measurement system is. If you can’t correctly count the number of variations happening can you really call them variations? Your measurement system is only as good as your accuracy, so it makes sense to spend a fair amount of time ensuring that not only are you counting defects, but you are counting the correct defects. This goes back to knowing why you want to measure something. If you want to find out why your shipments are late, measuring the number of birds around your facility won’t help. So accuracy needs two things: measuring the right data and ensuring the data is being measured in a way that answers your question.
Is it precise?
We’ve talked about precision and for a refresher precision is the reduction in variation. When you have identified your improvement area in the process, you are now ready for precision. So you are going to take one process, completed by the same person, in the same order every single time. Once you have identified this, you can began to reduce the variation and create precision.
Can you reproduce it?
The thought behind automating any process is ultimately making it scaleable, that is can you repeat the success? This is what determines a successful process from a failed one. Any process is good in theory, but where you get a great process is when you find one that can be repeated with the same amount of variation no matter who does it. That’s your end goal folks.
So we’ve covered the 3 basic characteristics of a Measurement System Analysis, so have a conversation with your belt and figure out your current state and your future. Your MSA will heavily influence your future, so take this conversation seriously. If you need more help, give us a call and let us help.
As we go over Six Sigma statistics, we have to talk about normal distribution. Before we get to that though we have to talk about why distribution is important to the way you interpret your data. In interpreting your data there is something you should know before you tackle how the information observed, confidence intervals. Confidence intervals is more complicated than this blog, but basically what you need to know is the greater the confidence level the less likely the variation is to occur and the more you can guarantee the accuracy of data analysis. In confidence levels there are 3 common ones that we use in data analysis, 99%, 95% and 90%. The standard of measurement is 95%, the higher the better but as a baseline 95% is a solid analytic benchmark.
Okay so back to normal distribution. Here’s what you need to know.
What is it?
You find normal distribution when you take all of your data and create a visual representation of the information. You will illustrate when recurring variations show up in your process. It is actually more helpful when you have a distribution that isn’t normal because then you can say ‘Aha it was the 3 hour traffic jam that affected the process’. When you hear people talk about the curve, this is what they are referring to.
When do you use it?
This is a tool that is best when used as a continuous probability model with measurements that you don’t have to create. Think about the weight of a cargo shipment or the number of a specific product you receive.
Raw scores and Z scores
Each normal distribution will have a raw score which is made up of two parameters: the mean and the standard deviation. The Z score measures how far you varied from a particular point on your data line. In real terms it means, if you want to see how many errors occurred on the 5th then standard deviation shows you that.
Why is it important?
The area under the curve shows the proportion of the curve and which tells you how important this data is to your business. Is the curve is small then you now that the distribution occurs within a relatively small set of circumstances which is easier to control within process. A wider distribution shows you that your process can be interrupted by a variety of factors and may need you to keep a close eye on it.
This blog is about Six Sigma data analysis. Because statistics are such a big part of the Six Sigma world, it makes sense that we talk about the data that is gathered and what it means. So here we go….
There are different types of data and anytime you measure something you going to need how to interpret it. There are two main types of data: attributive and variable.
Some people call this the most basic form of data, but for business purposes I don’t accept that. Qualitative data is simple in the fact that it is generally data that can be gathered by asking a yes or no question. For example, ‘Did they buy the new product?’ What is limiting about attributive data is that you really can’t analyze the results in a meaningful way, but it can give you a pretty good place to set your focus.
Variable data is also called quantitative and this is the data that you can measure and analyze. In order to decide if data you have is variable ask yourself these questions:
- Can you classify the data and count the results? (Think number of defects for a particular product line)? If you can this is called discrete data and the limitation of discrete data is that it cannot be broken down into smaller measurements to create additional meaning. It’s a one hit wonder.
- Can the data be measured on a time line with meaningful divisions (Think time, production speed, delivery dates etc…) If you can this is called continuous data and it can be divided further to create additional data.
As with all of these blogs, this is to get you started and statistical data clearly has more to it than one paragraph. But information is the first step and one you know what type of data you have, you have a better idea of what you need to know. Give us call and we can help you create where you need to go next.