80/20, Normal and other math

Rule, curve, model

Ideas that can be of assistance, as guides and suggestions

80/20

80% of land in Italy owned by 20% of people

80% of results from 20% of the causes

Pareto, Italian economist

(1828-1923)

Juran, American statistician, process improvement, often mentioned along with W.E. Deming

(1904-2008)

Use of 80/20 depends on goals, purpose

More equal

More results

Less effort, less expense

80 and 20 might not always be the best numbers, could be 90-10 or 99-1

Term “80/20 rule” used by Tim Krause in this room to describe work on the web and likelihood of this or that happening

I was surprised at the results on Amazon when searching “80/20”

I bought “80/20 Your Life” by Zahariades and was surprised by the result of thinking about his message and how I might apply it. My reading and my book purchases and my realization that many valuable books get their message across in the first part of the book seem open to shortening my read of certain books.

Quality control and process improvement people may concentrate on the low chance of a big error or mishap.

Normal curve

People sometimes expect the curve to be empirical and it can be

See the images of “Galton board”

But there is a formula that is used to make the curve

http://davidmlane.com/hyperstat/A25726.html

The height (ordinate) of a normal curve is defined as:

where μ is the mean and σ is the standard deviation, π is the constant 3.14159, and e is the base of natural logarithms and is equal to 2.718282.

x can take on any value from -infinity to +infinity.

f(x) is very close to 0 if x is more than three standard deviations from the mean (less than -3 or greater than +3).

This formula and the ideas connected to it have a rich and romantic history. The Belgian statistician thought the model expressed God’s will

We could get all philosophical about what the model shows and what God’s will might be.

I have found it easier and more widely acceptable to pay attention to the Galton board.

In the case of events, we get led into probability

The Normal Curve/Galton board model is about a ball hitting a peg and falling on one side or the other.

The chest measurement of Scottish soldiers

Another model that statisticians use: the Poisson curve/model/formula

This model is sometimes called the curve of rare events

As events speed up and more occur, it approaches the normal distribution

Examples of this distribution are: (from Plain English Wikipedia)

    • The numbers of cars that pass on a certain road in a certain time.

    • The number of telephone calls a call center receives per minute.

    • The number of light bulbs that burn out (fail) in a certain amount of time.

    • The number of mutations in a given stretch of DNA after a certain amount of radiation.

    • The number of errors that occur in a system.

    • The number of Property & Casualty insurance claims experienced in a given period of time.

I like flat tires, Supreme court vacancies and probability of a Prussian soldier being kicked to death by his horse. It too has a formula

This is not as weird or complex as it may look. The Excel spreadsheet and the analogue in Google Sheets (free) can create Poisson distributions.