*Piuss*

#
All 14 entries tagged

View all 376 entries tagged *Piuss* on Warwick Blogs | View entries tagged *Piuss* at Technorati | There are no images tagged *Piuss* on this blog

## January 05, 2013

### Lets define types of actions!

Statistical Process Control involves different types of actions. To sum up in short way, while applying SPC to company’s real process the following actions was taken:

**Taking actions on the process.**This comprises the Voice of the Process identification by using Control Charts. It can be considered as a first step to process improvement as it recognize assignable causes of variation.**Taking actions on the process outcomes.**This involves the Voice of the Customer identification. Here a person needs to separate acceptable outcomes from unacceptable.**Taking actions to align the two voices**. As a result of two previous actions, now a person seeks to compare the voice of the process with voice of the customer.

To my mind, this is a basis of SPC and those simple actions can be applied to almost any process. Now, I can easily understand those people in the companies, who put every action on control charts – I try to do the same with all figures that I find.

## January 04, 2013

### Fast tips to Statistical Process Control

While writing PMA many interesting points came to my mind and contribute to better knowledge of Six Sigma. These are the following thoughts that can be applied to almost any process:

- Identify measures that you daily face with. For example, in fashion retailing company that I was studying, managers were routinely collecting the data, but didn’t know what would happen next – how they would measure the process with that data. Thus, before collecting, identify propose and try to foresee what kind of data you may need for measurement.
- Adapt data. It is vital to filter any noise factors from the process. If you don’t, the process behavior chart will be bias and useless and will show you wrong result.
- Put the data into the context. The process behavior charts will help to consider information globally and see the whole picture of the process.
- After analyzing if the process is under control the voice of the process should be compared with the voice of the customer to find out if the process suits to customers’ expectations.

This is just a small part of SPC – quick tips. I still have lots of questions. But, these basics can be applied not only in terms of Six Sigma project or SPC, they are the rules for business to stay “healthy” and “wealthy” all the time.

## December 23, 2012

### Bell Curve

To analyze the process in the company, it is essential to learn about process first, then to illustrate the process by charts and diagrams. Thus, after learning and describing the process, the individual and moving range charts were created to illustrate the process. Then to identify how process suits to customers’’ requirements the process capabilities were calculated. At this stage I face a problem – how to illustrate those calculations?

As I understood, this is a six-sigma logic, if you want, - first, to calculate and then illustrate results. Unfortunately, I didn’t know how to illustrate the process capabilities. I knew how picture should look like with Cp = 0,351 but couldn’t find the formula that helped me to build the graph. Luckily, I found an article where the application of Gaussian Bell Curve to six sigma project was described.

So what does, basically, Gaussian Bell Curve can show? The main aim of this function is to consider the distribution of the process. If the points of our process is distributed “Normally”, then around 68% of the points should lie within one standard deviation of the mean, 95% of the points should lie within two standard deviations of the mean, and 99.7% of the points should lie within three standard deviations of the mean.

Although the Gaussian Bell Curve is useful tool in six sigma analysis, its calculation is complicated, as was mentioned in the article. The Cp and Cpk calculations are much simpler and provide you the same results. Moreover, by calculating process capabilities you can also get picture of the process’s distribution. Maybe, it will be not as clear as using Gaussian Bell Curve but its calculation will be, definitely, less time-consuming.

## December 12, 2012

### Presenting data in context

Almost every company compares one number with another number. It is so easy to do and to their point of view this comparison can provide the evidence that process is below or above the target. Is it? Can we really judge how good our business operating by such simple comparison?

All information that we get from others we put in the context. So why then figures and numbers should be considered independently? Statistical Process Control suggests to build a flow chart and then also put natural limits of the process, thus, to present figures and numbers in the context. This is reasonable and it makes sense, BUT…what I cannot understand and agree with is that this traditional ways of communication with numbers are considered to be useless.

As Wheeler states this comparison cannot filter out the noise of the process. Why not? For example, if we develop target with taking into account economic environment and seasonality (two noise factors) and compare it versus actual numbers in this way we do filter out the noise of the process. After that we can use obtained data and put it into the context by using control chars. I do believe that this traditional comparison is useful. If not, then why everybody is still using it?

## December 09, 2012

### Identifying quality characteristics

Which tool to use to identify quality characteristics of the process? And what do you mean by quality characteristics? These are two main questions which I faced during PMA writing.

The quality characteristics are usually a measurement of the process. And **SIPOC** diagram involves the measurement of the process identification consequently I can use it as a tool. But SIPOC is commonly considered as a tool for describing the process, not identifying how it can be measured. In that point of view SIPOC is not the best choice. Can we then use **fishbone diagram** logic to identify the characteristics? Fishbone diagram enable to develop those characteristics through 5 factors: methods, materials, people, environment, and equipment. But it usually applied when the need of cause and effect analysis appeared. A good combination of SIPOC and fishbone principles is presented in **CTQ tree. **Using this tree you focus on customers’ expectations, which can be taken from SIPOC diagram, then for each customer expectation you develop the key characteristics which are essential to satisfy the customer. And this CTQ tree uses the same logic as fishbone diagram – it describes the characteristics by combining them in different groups (drivers). In case with fishbone these are 5 factors.

CTQ tree seems to be most appropriate tool that helps to identify quality characteristics of the process, there are lots of others tools, but CTQ provides a highly descriptive approach with a good visualization.

## December 02, 2012

### Filter out the noise

Never thought that creating a Control Chart can take so much time. You have to consider almost everything:

- The nature of the process. If it have subgroups or not.
- The size of the sample. Sometimes 10 values cannot show the whole picture, so it is better to take at least 20
- Finally, noises of the process. Before building a chart, make sure that you filter out the noise factors.

The last requirement really drove me into a corner and I stuck. How can I take into account such noise as *seasonal character of the sales*? Or, for example, I took a small selling company which opened its branch not so far ago, so I also had to consider the *growth rate of the company*, but how??? After two days of agony I still didn’t have any answer, but then I sudenly stumble across the report, where company described how they developed sales targets. They were wrighting that each monthly target was developed according to expected growth of the business and sales seasonality. After that I decided to take figures of sales performance comparing monthly targets (sales/target). In that case, the noise factors were filtered as it was taken into account earlier in targets development.

This time I managed this task somehow, but I really believe that noises in some processes cannot be filtered out so easily.

## November 29, 2012

### SIPOC rules!

I am now learning about the selling process in one small fashion company and I must say that SIPOC really helped to understand the process better and identify possible quality characteristics.

I and the owner of the company (this is my aunt) spent the whole day on thinking and filling in the SIPOC Diagram. The more we went deeper into the process research the more obvious its characteristics appeared. For example, we identified few steps into the ordering and selling process, then we filled in measures for each step, present data, goals, sources of variation and the impact on business. When we came to the last criteria (impact) she told me that basically there are only two sub-processes or steps that really affect the business. We then realized that her company don’t control these strategically important sub-processes because she couldn’t provide any data in that field. Finally, we came to the conclusion that from now on she will regularly monitor these two sub-processes and collect the data for further analysis.

In the end of the day she told me that I made her to reconsider the way that she used to operated her business. Wow…, I now can see clear the "output" of my studies and happy "customer"))!

## November 28, 2012

### Steps in Statistical Process Control

As I probably mentioned before I decided to choose PIUSS topic related to the Statistical Process Control, which I can actually apply to a process of some small company. So, when I usually try to apply theory on practice the first thing that I do is identifying the steps of implementation. It shouldn’t take much time, but not in this case.

The problem is that Statistical Control appeared before Six Sigma. So, while early school of statistic analysis and control suggest 9 steps following each other in a particular order, Six Sigma combined and comprise this steps into DIMAC circle in another order. Thus, according to early studies, as the second step, just after the process description, goes cause and effect analyses, whereas in DIMAC we meet this analyses almost im the end stage “Analyse”, where the Pareto and fishbone diagram can be used to identify causes and effects and its relation by Scatter diagram.

Where is the truth?

## November 26, 2012

### To build control chart

Today I tried to identify what are the differences between two types of control charts: average and range chart VS individual and moving range charts. It was important for me to know the key features of both charts, because I wanted to use one to control the sales process.

As I understood, to decide which chart to use you have to know how many subgroups you will consider in your process. For example I am considering sales – so, basically this is ONE subgroup, which means that I need to use Individual and Moving Range Chart. If I had 3 or 5 subgroups it will be much easier for me to use Average and Range Chart. It seems to be not so difficult, BUT!!! One thing is choosing and building a chart and another is analysing and describing it.

## November 22, 2012

### Stop and learn first!

During this week with PIUSS we had many case studies and experiments. You know sometimes one experiment can teach you more than 100 lectures. I tried to apply SIPOC to airplane production and design a helicopter using Taguchi methods. This gave me some knowledge of how to apply Six Sigma approach and Taguchi to a real situation. Doing Six Sigma experiment with the airplane I realized that we were focused on the result all the time and didn’t pay as much attention to the learning about the process as we should. I think, it is extremely important to study the process first.

If we think about the Six Sigma as a practical guideline or a cookbook for companies’ transformation it becomes clear that it involves practical approach, where every cause of variation can be translated into a cash and every process has a deadline. So, what else can we expect from this practical tool! Of course, if you want a quick recipe to transformation than you have to be ready that you won’t go to deep to the analyses - just because of the lack of time. But maybe this is a reality, - we don’t have time in our modern world to think.