# Beyond the Basics

**Abstract:**In 1976, a team from the Union of Japanese Scientists and Engineers (JUSE) collected the "new seven" quality tools: affinity diagrams, arrow diagrams, matrix data analysis, matrix diagrams, process decision program charts, relations diagrams and tree diagrams. An affinity diagram is a tool for organizing brainstormed ideas by grouping them into categories or themes; this can promote creativity and help groups overcome idea paralysis. An arrow diagram is a simple tool for illustrating the order of activities in a process or project and identifying collections of critical processes that must be completed as quickly as possible. Matrix data analysis is the only tool on the list that has changed significantly in 35 years, but it remains a way to examine multidimensional data of the sort that often exists with complex industrial problems. Matrix diagrams offer a visual representation of the relationship between groups of information. Process decision program charts (PDCPs) are another visual tool …

### Social Bookmarking

Digg, delicious, NewsVine, Furl, Google, StumbleUpon, BlogMarks, Facebook

Error in Figure 8? Seems that the coloring of the blocks does not match their description in the text.

--F Nagy, CQE, CQA, 04-26-2012

Gilles,

Thanks for the feedback. I see your point. The correlation coefficient table is used to arrive at the characteristics values and vectors in the subsequent step in the bibliographical source as a step-by-step approach. If you were to use MINITAB 16 statistical software, you will obtain step three output directly from the step one inputs. I could have made the statement more explicit using MITAB 16 statistical software. Even though I used MINITAB 16 to get to the analysis and results, I still wanted to follow the process steps as outlined in the bibliographical source. I agree this is not the easiest tool of the 7 new tools. It took a lot of time to research, write and edit this small portion of the article.

Regards,

Govind

--Govind Ramu, 04-25-2012

I really appreciate the review of these tools in the QP magazine. The article also provides an opportunity to understand how Multivariate analysis can help to see correlation among several variables with a lot of data. This tool is not the easiest to grasp, and I took this opportunity to dive into the analysis process with Minitab 16 using the original files kindly provided by Mr. Govindarajan Ramu.

If I can suggest one thing, it would be to explain the added value of the Correlation Coefficient matrix to the reader and how it is connected to the Table 4 values. I am not sure I see how they are interrelated.

Thank you,

Gilles Belanger, P. Eng, CQE, CSSBB

--Gilles, 04-22-2012

Joel:

Thanks for the detailed feedback. The "very little reference" I mentioned in my article refers to finding answers for "What is Matrix data Analysis?", "What did JUSE originally consider as Matrix Data Analysis?" I did an extensive bibliographical research using ASQ Knowledge Center historical archives, Quality Information Search, Google search, Wiki and my own collection of 100+ quality books! The Japanese author Shigeru Mizuno's Management for Quality Improvement: The Seven New QC Tools (Productivity Press, 1988) is the only one I found that refers to Matrix Data Analysis and explains it as a collection of Multivariate analysis tools. This author used the Principal Components Analysis as an example to explain Matrix Data Analysis. Of course, after we identify the tools JUSE considered as Matrix data analysis, there are plenty of reference materials available for the individual tools. In my opinion, Quality Progress is a magazine that intends to cover a wide range of quality topics from various industry sectors targeted at readers of all levels of experience and education. Sometimes, QP articles have reasonable statistical depth associated with an application. Readers looking for more advanced statistical techniques associating with applications could benefit from magazines such as Quality Engineering, Quality Management Journal, JQT, etc.

Regards,

Govind

--Govind Ramu, 04-12-2012

Great and useful information. Refreshing topics.

--Jack Rezvany, 04-11-2012

Nice summary.

--Frank Wells, 04-11-2012

Beautifully written and well presented. It has a very good reference and also application value.

Dr. R.H.G. Rau, Management Consultant, Hyderabad, INDIA

--RAU R.H.G., 04-11-2012

The above article is mind blowing and a great value-adding material for data analysis, especially for getting top management buy in in terms of funding for quality-related issues.

--monica Nwosu, 04-10-2012

Great tools.

--carlos, 04-09-2012

Personally, I find the new quality tools to be relatively light on the statistical analysis side. For instance, the article states, "There is very little reference material on matrix data analysis itself." On the contrary, there are many books on linear modeling and years of articles in statistical journals that establish these techniques. Some books to consider include the Box and Draper classic, the Box, Hunter and Hunter classic, the RSM book by Myers and Montgomery, and Variance Components by Searle. The article repeatedly refers to step-by-step approaches. For a step-by-step approach, one might also consider stepwise linear regression a la the book Applied Linear Statistical Models by Kutner, et. al., or stepwise logistic regression, like in JMP software. For building trees, one might consider CART, a data-mining tree-building method. For risk management, one might want to consider using maximum likelihood estimation of lifetime distribution parameters for multiply censored lifetime data. See the book Statistical Methods Reliability Data by Meeker and Escobar, or the new edition of Applied Reliability by Tobias and Trindade, or the JMP book on Reliability. We can also include various covariates in such lifetime models, to account for accelerated lifetime modeling. Bayesian methods are becoming more and more popular in decision making. See the Jim Berger book called Statistical Decision Theory and Bayesian Analysis. See also the Hierarchical models book by Gelman and Hill or Gelman's Bayesian Data Analysis. My opinion is that the ASQ associated journals like JQT and Technometrics include many useful techniques that are not enough included in the Quality tools. I would like to see statistics play a much larger role in the quality certifications and quality tools. This is just my opinion. Perhaps others will agree?

Regards, Joel Dobson, an accredited Professional Statistician per ASA, CQE per ASQ, and CSSBB per ASQ.

--Joel Dobson, 04-09-2012

### Average Rating

Out of 8 Ratings

Rate this article

#### Related Articles

One Good Idea: Improve Product Development Using IPD

Quality Attitudes Start in Childhood

Quality in the First Person: Perfectionists Make Bad Machinists

Featured advertisers

Would it be a good idea to mention about the softwares how to implement the quality tools?

--Aylin N. Sener, 06-04-2012