Murphy's laws and other wisdom on data analysis

“A silly theory means a silly graphic.” — Edward Tufte

“It is better to solve the right problem approximately than to solve the wrong problem exactly.” — John Tukey

“All models are wrong; some models are useful.” — George Box

“Don’t fall in love with a model.” — George Box

“The complexity of a model is not required to exceed the needs required of it.” — D. Silver

Murphy’s law: If anything can go wrong, it will.

Box’s law: When Murphy speaks, listen.

Law of ubiquitous role of data mining: In God we trust. All others bring data.

Murphy’s law on machine learning: The number one cause of computer problems is computer solutions.

Menger’s law on modeling success: If you torture data sufficiently, it will confess to almost anything.

Murphy’s law effects on data:

Kordon’s law on computational intelligence: Computers amplify human intelligence.

Positive Corollary: Smart guys get smarter.

Negative Corollary: Dumb guys get dumber.

Murphy’s law on rule-based systems: Exceptions always outnumber rules.

Murphy’s law on sources of fuzzy logic: Clearly stated instructions will consistently produce multiple interpretations.

Source:
Computational Intelligence Marketing
Arthur Kordon, The Dow Chemical Company
SIGEVOlution, 4(1): 2-11, 2009.