On P-Values and Significance Testing

"What is the probability of obtaining a dead person (D) given that the person was hanged (H); that is, in symbol form, what is p( D|H)? Obviously, it will be very high, perhaps .97 or higher. Now, let us reverse the question: What is the probability that a person has been hanged (H) given that the person is dead (D); that is, what is p( H|D)? This time the probability will undoubtedly be very low, perhaps .01 or lower. No one would be likely to make the mistake of substituting the first estimate (.97) for the second (.01); that is, to accept .97 as the probability that a person has been hanged given that the person is dead. Even thought this seems to be an unlikely mistake, it is exactly the kind of mistake that is made with the interpretation of statistical significance testing---by analogy, calculated estimates of p( D|H) are interpreted as if they were estimates of p(H|D), when they are clearly not the same." (Carver 1978)

This is just one among many nice quotes and observations on significance testing that have been organized by David F. Parkhurst (School of Public and Environmental Affairs, Indiana University)

To Say the "Data Are" Is Simply Wrong!

"The English word 'data' is not a plural.  It is an aggregative noun, like 'rice' or 'grass,' referring to a large mass of stuff made up of tiny objects more or less indistinguishable from one another.  Such nouns take the singular form of the verb in English:  'The rice is cooked.  It is indeed true that the Latin word data is a plural; but then, as I keep telling editors, if the Latin word is what they intend, they should print it in italics ..."

--- from the web version of John Derbyshire's review of Charles Murray's Human Accomplishment: The Pursuit of Excellence in the Arts and Sciences, 800 B.C. to 1950.

IMHO, This useful quote should be pinned to the office wall of every editor of statistical articles.

BACK TO: J. Michael Steele Home Page or The Rants List