# Tools & Techniques

### What should you do if your data isn't normal, even after a transformation?

It is possible to analyze non-normal data when conducting a capability analysis – even if it cannot be transformed to a state of normality.  Of course, this position assumes that the underlying distribution is unimodal in nature (i.e., not multimodal).  Technical details aside, this particular type of problem can quickly become an analytical nightmare for…

### In a Pareto chart, 20% of the causes represent 80% of the problem but there are never 20%…usually there are more. Why is this?

The gentlemen referred to as “Pareto” long ago advocated that 80 percent of the world’s wealth was controlled by 20 percent of the world’s population.  This phenomenon is also called the “Pareto Principle,” and will be designated as “PP” for our discussion.  For the case just given, it should be noted that the 80 percent…

### While calculating Pp and Ppk, how do I determine the value of Short term and long term Standard deviation?

One must necessarily understand that the short-term standard deviation reports on the “instantaneous reproducibility” of a process whereas the long-term standard deviation reflects the “sustainable reproducibility.”  To this end, the short-term standard deviation is comprised of the “within group” sums-of-squares (SSW).  The long-term standard deviation incorporates the “total” sums-of-squares (SST).  Of course, the difference between…

### If you are only allowed to select a handful of tools in the six sigma tool box, what are the tools you will select as the key ones?

It is now late in the evening as I prepare an answer to your question.  Maybe it’s the fatigue after a day of providing answers or perhaps it’s the nature of the question, but what really grabs me about your question (perhaps in the wrong way) is the word “tools.”  From a different perspective, I…

### What do you do in automated manufacturing environments, hospitals, telecom centers or data centers where equipment uptime is so critical?

Based on the elements of your question, I would say that your problem could be readily shaped into a Black Belt project.  I would assume that a Pareto analysis has already been conducted. As a more advanced diagnostic, you should consider employing a multi-vari chart.  Although simple in nature, such a chart has considerable power. …

### Could you explain the best way to predict the outcome of a process in the future?

Reference the quality literature on statistical process control, also known as “SPC.”  There are many excellent books on the subject, particularly the one by “Grant and Levenworth.”  Process improvement and optimization is often accomplished by way of statistically designed experiments, or “DOE” as it is known.  To this end, the work of “George Box” is…

### How does normality of the data impact the process performance?

First, there is a great deal of literature on this subject – find it and read it.  However, there is no substitute for direct experience.  Of course, this is directly related to the old saying “we learn by doing.”  Along these lines, I would strongly recommend that you further your Six Sigma training and education…

### How can I separate process, product, and machine capability?

Many quality practitioners treat product and process capability as if they were interchangeable concepts.  Presumably, this convention has evolved over time due to the naturally strong correlation between the two.  However, it would not be my recommendation to view these two concepts in the same light. At the risk of leading a dead horse to…

### What is the best way to develop a CTQ tree?

The best way to develop a CTQ tree is the form of a cause-and-effect matrix.  Locate CTQ’s on columns and CTP’s on rows.  Each column-row intersect constitutes a “causal opportunity,” the strength of which must be rationally measured or otherwise evaluated.

### In Minitab on the Poisson plot it plots expected defects versus observed defects. Where do the expected defects come from?

As you likely know, the Poisson distribution is an approximation of the binomial.  In general form, the Poisson function is given as Y = (np^r * e^-np)/r!, where n is the number of trials, p is the event probability, and r is the number of event occurrences.  By direct substitution, we assert that Y =…

### My project is to "reduce the attrition rate of employees." How I should go about process mapping this?

As stated in your question, the project is focused on the “attrition rate of employees.”  At first glance, this would appear to be a problem – not a process.  Given the problematic perspective, we must recognize that “attrition rate” is a critical-to-value characteristic (CTV).  As such, it should be known as the dependent variable (primary…

### When should data be excluded from cpk analysis?

Obviously, a suggested course of action should be quite guarded, as it would be very case sensitive (i.e., circumstantial by nature).  As we all know, some consultants make their living resolving such “catch 22” situations.  We also recognize that the ability to find a balance point is more art than science.  It is much like…

### Must a Black Belt use all Six Sigma tools on every project? Is it common not to use all tools?

1) There is no such thing as a one-size-fits all Black Belt or Green Belt program of study. 2) Many customers are naïve.  They often want more tools (not fewer), regardless of whether or not they will ever be used. 3) Some customers seek to purchase a hardware store so as to fix the kitchen…

### I am gathering attribute data. Sample size is 5 pieces. I collect 20 samples with zero defect. How do I calculate ppm and Cpk?

Under the condition that D = 0 defects for the constrained condition of N = 20 samples, we can statistically approximate the short-term capability and provide its quantity in the form Z.st = 3.33.  Of course, this is directly equivalent to Cp = 1.11. Interestingly, the statistical base underpinning this set of computations is fully…

### What is the difference between SPC and SQC?

There is little difference between Statistical Quality Control (SQC) and Statistical Process Control (SPC).  At one time, there might have been some philosophical separation, but today, they exist as general synonyms.  Some prefer SQC because the idea of “quality” is larger and more encompassing than that of “process.”  Others counter this by pointing out that…

### How do you determine the Xs in the analyze phase of DMAIC?

Establishing the initial list of potential causes is often more art than science.  Unfortunately, the brainstorming process is still one of the best ways to surface candidate variables.  However, there are several other alternatives: 1)   Query process experts. 2)   Benchmark similar processes. 3)   Review the literature. 4)   Perform an Internet search. 5)   Conduct correlation study….

### Can you explain "degrees of freedom" and provide an example?

To facilitate an answer, we will consider three examples.  First, consider the game of baseball.  We understand the field-of-play consists of 9 positions.  The coach is “free” to assign any of the 9 players to any of the 9 positions. Once the 8th player is assigned to the 8th position, the 9th player-position is pre-determined,…

### Can you suggest a specific quantifiable problem in Robust design and/or Six Sigma for PhD studies?

Suppose we consider a specific bilateral critical-to-quality characteristic (CTQ).  In other words, we are in view of a key design feature that sports a two-sided performance specification.  If a bilateral design margin of “Y percent” was to be imposed on the given CTQ (during the course of product configuration), we indirectly and necessarily infer the…

### Can you explain "degrees of freedom" in the context of a Six Sigma tool, such as a DOE?

Let us suppose we are interested in testing the influence of a certain independent variable (say, A) as it relates to a given dependent variable (say, Y).  We will suppose the experimental factor (variable A) is to be tested at two competing settings (test levels).  In this scenario, the two levels will be called “high”…

### Can you please explain "acceptance sampling"?

Arguably, acceptance sampling is an effective and efficient means to ensure the proper surveillance of product and service quality.  Using this approach, a random sample (of product or service) is inspected or tested to determine if the observed level of quality is acceptable or unacceptable.  If the sample supports the hypotheses of unacceptability, then certain…

### How do you suggest I process map a process like "deliver enhanced value to the customer"?

Please recognize that the “art and science” of process mapping is quite generic by nature.  You should apply the mapping tools, techniques, and procedures in the given situation just as you would in any other type of situation.  Granted, the variable labels will change – but that’s about it.  Simply stated, you must define what…

### Is there any experience with improving the adhesion of water based paint (spray system) on metal surfaces?

Thanks to modern technology, we have before us a virtual mountain of information.  On the Internet, we can find many case studies on the subject of DOE (design-of-experiments).  For a wide area success stories and general discussion, you may want to visit the following websites: 1) http://www.statease.com/articles.html2) https://www.isixsigma.com/tt/doe/3) http://class.et.byu.edu/mfg340/lessons/designofexperiment/4) http://members.cox.net/asqsd/kn/publications.htm In addition to these sources,…