Improvement Insights Blog

An Easy Way to Tell if Data is Variable or Attribute

Six Sigma students are often confused by terminology. Variable and attribute data are often confusing. Calling it measured or counted doesn’t help that much. Here’s a way to explain it that almost everyone can understand quickly.



“Early on when I was teaching Quality Improvement, people kind of struggled with the whole idea of variable and attribute data, and telling them that it was measured and counted didn’t seem to help a lot.

“As a programmer, the way I think about it is: If it has a decimal point, it has to be measured, right? If it’s an integer, it’s most likely counted, right?

Continue Reading "An Easy Way to Tell if Data is Variable or Attribute"

Posted by Jay Arthur in Improvement Insights, QI Macros, Statistics.

Use XmR Charts instead of c, np, p and u Charts

I have found that an XmR chart is the easiest way to display attribute data. Simply convert the numerator/denominator into a ratio and plot the ratio.

• defects per day could be a c chart, but an XmR chart works just as well
• defects/samplesize could be np, p or u chart, but XmR chart works just as well using the ratio

Almost two decades ago, Tom Pyzdek said: X chart provides an excellent approximation to the p chart.

More recently, Donald Wheeler noted that XmR chart limits will be very close to c, np, p or u chart limits if the underlying distribution is correct.

Continue Reading "Use XmR Charts instead of c, np, p and u Charts"

Posted by Jay Arthur in QI Macros, Six Sigma, Statistics.