What’s in a Name?

Stigler’s Law of Eponymy states, “No scientific discovery is named after its original discoverer.” It was named by Stephen Stigler, who credits the notion to Robert K. Merton (1910-2003). Stephen Stigler’s father, George Stigler, won the Nobel Prize in Economics in 1982. Robert K. Merton’s son, Robert C. Merton, won the Nobel Prize in Economics in 1997.

The Pareto chart that we know today was introduced in 1950 by Joseph Juran2 (1904-2008). It’s named for Vilfredo Pareto (1848-1923), an Italian economist who had noted that, for instance, about 85% of the wealth in Milan was owned by 15% of the population and that 80% of the land in Italy was owned by 20% of the population.  Juran observed that in many quality improvement situations, a high percentage of the problems were the result of a handful of causes. At one time, Juran referred to this Pareto principle as the ‘vital few and the trivial many’ but later changed that expression to the ‘vital few and the useful many.’ The Juran Trilogy – Quality Planning, Quality Control, and Quality Improvement – is named for Juran, who himself referred to it as the Quality Trilogy.

Student’s t-distribution was developed by William Sealy Gosset (1876-1937), and originally was referred to by the letter z (which in later years came to represent the normal distribution). Gosset worked for the Guiness brewing company, and published under the pseudonym “Student” for reasons of confidentiality. Most of Gosset’s work was published in Karl Pearson’s (1857-1936) journal Biometrika, but it was Sir Ronald Fisher (1890-1962) who had the greater appreciation for Gosset’s work with small sample sizes. Fisher and Pearson could not stand each other, perhaps in part because Fisher exposed a flaw in Pearson’s use of degrees of freedom in the Chi-squared test.

The Bland-Altman plot is a scatterplot of mean differences (represented by the y axis) vs. average values (represented by the x axis). It was introduced in the early 1980s by Martin Bland (1947 – ) and Douglas Altman (1948 – ). It is identical to the Tukey mean-difference plot, introduced several years earlier by John Tukey (1915-2000).

The Cooley-Tukey algorithm for Fast Fourier Transforms was developed by James Cooley (1926-) and John Tukey, whose results were published in 1965. Some years later, it was observed that much of the Cooley-Tukey algorithm had been invented in 1805 by Carl Friederich Gauss (1777-1855), the great German mathematician known for his many mathematical and scientific contributions, including his work with the normal distribution.

The probability density function for the normal distribution, often called the Gaussian distribution for Carl Friederich Gauss, was first described formally by Abraham de Moivre (1667-1754) in 1733. Gauss contributed to the development and use of the normal distribution, especially as it relates to measurement error (‘the normal law of error’), as did Pierre-Simon LaPlace (1749 –1827) and others. Sir Francis Galton (1822-1911) referred to the normal distribution as the normal distribution in 1889; his protégé Karl Pearson referred to the normal distribution as the Gaussian distribution in 1905.

The Deming Cycle – Plan, Do, Study, Act – is named for Dr. W. Edwards Deming2 (at one time, the cycle included the term Check instead of Study). Deming credited Walter Shewhart for the development of what we now call the Deming Cycle. It is the precursor to DMAIC (define, measure, analyze, improve, and control), popularized in six-sigma programs. DMAIC itself was originally MAIC, but someone figured out you had better define what you’re solving before you start measuring.

Walter Shewhart (1891-1967) developed the first control charts in the 1920s, which are often referred to as (appropriately enough) Shewhart control charts. Sometimes people refer to control charts that came after Shewhart’s work as ‘modern control charts’ which indeed are younger than Shewhart charts but still in many cases 50 or 60 years old.

Murphy’s Law, commonly cited as “Whatever can go wrong, will go wrong” is named for Edward A. Murphy (1918-2000), an aerospace engineer who said something along the lines of, “Well, I really have made a terrible mistake here, I didn’t cover every possibility.” The person who made Murphy famous is Dr. John Paul Stapp (1910-1999), known to many for his rocket sled research (“Gee Whiz”) and at one time the fastest person on earth (632 MPH on a sled).  In a press conference, Stapp referred to Murphy’s Law as we know it today and it took off from there. Those who have studied the origin of Murphy’s Law usually conclude that “Murphy’s Law applies to Murphy’s Law.”3

  1. http://www.juran.com/about_juran_institute_our_founder.html
  2. http://deming.org/
  3. http://www.improb.com/airchives/paperair/volume9/v9i5/murphy/murphy4.html
By |2017-09-18T22:54:36+00:00September 7th, 2010|The Data Blog|Comments Off on What’s in a Name?

About the Author:

Syntricity Corporation is the number one provider of test management and optimization software for the semiconductor industry. Built for the future of analytics, enterprises worldwide rely on Syntricity for data integration, data quality, and big data solutions that accelerate product ramps and deliver premium yields. A privately-held company, Syntricity is headquartered in San Diego, California. For more information, send e-mail to brian.graff@syntricity.com, visit www.syntricity.com, or call 858.552.4485.