Wednesday, March 23, 2011

i-TFTD #310: On the Use of Data

#310-1. If you torture the data long enough, it will confess.
-Ronald Coase, Nobel prize-winning British economist (1910-)

#310-2. Far better an approximate answer to the right question, which is often vague, than the exact answer to the wrong question, which can always be made precise.
-John W. Tukey, American statistician (1915 – 2000)

#310-3. The temptation to form premature theories upon insufficient data is the bane of our profession.
-Sherlock Holmes, brilliant fictional detective created in 1887 by Arthur Conan Doyle, Scottish author and physician

Statistical methods can be misapplied to create the illusion of conclusive proof, especially due to the wide availabil! ity and ease of use of tools to make charts of various types. In recent years I have keenly followed the explosion of infographics and data visualization.

For any non-trivial issue, it is important to spend time in formulating the right question before jumping to finding answers or gathering data. Many creative thinking techniques rely on redefining the question or problem statement, which can lead to interesting new dimensions to explore to come up with innovative solutions.

An interesting tidbit about John Tukey: He is credited with coining the word "bit" as a contraction of binary digit and a handier alternative to bigit and binit! He also coined the term "software".

No comments: