SPC

QCtrackingToyota1950sArtOfLean2

Jul 16 2019

Updating the 7 tools of QC

A conversation with Franck Vermet about problem-solving tools for factory operators caused me to revisit the 7 tools of QC from 50 years ago and ponder how they should be updated with current data science.

Data Science for Operators, as a book, remains to be written. If you google this phrase today, what comes up is training courses offering to “change your career” by attending a “data science bootcamp.” TIBCO Spotfire has “Workflow Operators” but these are programs, not people.

So the following are tentative answers to questions that haven’t been asked before.

Continue reading…

By • 11 • Tags: , , , , , ,

Mar 12 2019

More About the Math of the Process Behavior Chart

In statistics on time series with “moving” in their name, each value is correlated with past and future neighbors — that is, the series is autocorrelated. It affects the way you can use these statistics to detect anomalies and issue alarms.

The moving range in the XmR chart is a case in point. Its autocorrelation in the moving range chart is self-inflicted. It is autocorrelated by construction, regardless of whether the raw data themselves are.

Some raw data are autocorrelated. For example, when you issue a replenishment order for a part by pulling a Kanban from a bin, you are assuming that the demand for a coming period to match that of the period that just elapsed, with minor fluctuations. Implicitly, you are leveraging the autocorrelation of the part consumption across periods.

On the other hand, if a physical characteristic of a manufactured part is the sum of a constant and noise, then the noises are independent, and therefore uncorrelated. Taking moving ranges introduces an autocorrelation between consecutive values that is absent in the raw data.

Continue reading…

By • 7 • Tags: , , ,

Mar 2 2019

The Math Behind The Process Behavior Chart

Ever since asking Is SPC Obsolete? on this blog almost 6 years ago, multiple sources have told me that the XmR chart is a wonderful and currently useful process behavior chart, universally applicable, a data analysis panacea, requiring no assumption on the structure of the monitored variables. So I dug into it and this what I found.

Continue reading…

By • 45 • Tags: , ,

Feb 27 2019

Analysis of Oscar TV Viewership | Mark Graban | LinkedIn

“Initial analysis says Oscars TV viewers and ratings are up over 2018. But, for context, the ratings were DOWN in 2018 compared to 2017.

Instead of reacting to each new data point, look at trends over time using “run charts” or “process behavior charts” (as I created). Did having “no host” make any statistically significant difference in ratings? No. The numbers are just fluctuating. Don’t waste time cooking up an explanation for ‘noise’ in a metric.”

Mark Graban’s Oscar Viewership Chart

 

 

Source: LinkedIn

Michel Baudin‘s comments: What happened between 2004 and 2005? Visually, the downward step is the one feature of the chart that stands out. If the technique Mark used is valid, there should be assignable causes from that period to explain the drop. If you forget the green and red lines and just look at the time series, however, a smooth, long-term downward trend sounds like a better fit. Perhaps Mark should try more modern trend analysis tools besides the venerable XmR chart.

Following a day of spirited discussion, Mark sent me the data and asked for my own analysis, which is in the chart below. The gray band is a 99% confidence interval, calculated without any knowledge of the nature of the numbers. The points outside the band can be assumed to have assignable causes for their unusual high or low ratings, and I took a look at the press reports on a few. As you can see, there is nothing special happening in 2004-2005. 

The popularity of a show has nothing to do with a critical dimension on a manufactured part, which is supposed to be constant. The plant organization has the authority to do what it takes to keep it that way. There is no reason why show ratings should be constant.

In addition, while a length measurement qualifies as a raw data point, the published number of viewers of a TV show doesn’t. In the US, it is an estimate based on a poll of 5,000 households. Viewership of the Oscars ceremony in 2019 was 11.5% higher than in 2018. On 5,000 data points, it does not look like a fluctuation. By comparison, political polls use samples of 1,000 to 1,500 voters and claim margins of error of ±3%.

The viewership estimates aren’t just numbers in a table, and you can’t interpret them properly without knowing their backstory.

#SPC, #XmRChart, #ProcessBehaviorChart

Continue reading…

By • 2 • Tags: , ,

Dec 10 2017

Is SPC Obsolete? (Revisited)

Six years ago, one of the first posts in this blog — Is SPC Obsolete? — started a spirited discussion with 122 comments. Reflecting on it, however, I find that the participants, including myself, missed the mark in many ways:

  1. My own post and comments were too long on what is wrong with SPC, as taught to this day, and too short on alternatives. Here, I am attempting to remedy this by presenting two techniques, induction trees and naive Bayes, that I think should be taught as part of anything reasonably called statistical process control. I conclude with what I think are the cultural reasons why they are ignored.
  2. The discussions were too narrowly focused on control charts. While the Wikipedia article on SPC is only about control charts, other authors, like Douglas Montgomery or Jack B. Revelle, see it as including other tools, such as scatterplots, Pareto charts, and histograms, topics that none of the discussion participants said anything about. Even among control charts, there was undue emphasis on just one kind, the XmR chart, that Don Wheeler thinks is all you need to understand variation.
  3. Many of the contributors resorted to the argument of authority, saying that an approach must be right because of who said so, as opposed to what it says. With all due respect to Shewhart, Deming, and Juran, we are not going to solve today’s quality problems by parsing their words. If they were still around, perhaps they would chime in and exhort quality professionals to apply their own judgment instead.
Continue reading…

By • 3 • Tags: , , ,

Oct 23 2017

There Is More To Data Than Just Numbers

Don Wheeler’s Understanding Variation starts with a chapter entitled “Data are random and miscellaneous” that contains no discussion of any part of its title. Implicit in Wheeler’s book, however, is the view that data consists of tables of numbers, representing either measured variables — lengths, weights, densities,… — or event occurrence counts — defective units, defects, machine failures,…

Many times, I have quoted computer scientist Don Knuth on this subject, saying that data is “the stuff that’s input or output,” meaning anything that can be read or written, and it includes much more than tables of numbers. The data we work with today includes, for example, the following:

  • Unstructured text, like 25,000 incident reports written by maintenance techs all over the world in their versions of English about problems with jet engines, or thousands of product reviews posted by consumers on e-commerce sites
  • Images, like photographs of visual defects on products, or electron-microscope images of integrated circuits.
  • Videos recordings of operations.
  • …

Analyzing data about a manufacturing process today means extracting information from all sources. The state of the art, based on automatic data acquisition and databases includes analytical techniques that were unthinkable in Shewhart’s day, known under the labels of data science, data mining or machine learning.

Continue reading…

By • 2 • Tags: , , ,

1 2 3 4