RE: [S] Cox quote?

Edward Malthouse (
Fri, 10 Jul 1998 17:05:34 -0500 (CDT)

Thank you to all who responded my my question:

> Please excuse the fact that my question is not directly related
> to S-plus.
> I colleague mentioned a quote that I would like to track down the
> source of. She thought it was made by D. R. Cox.
> "All models are wrong; some are useful."
> Sections 1.1 and 1.2 of Cox and Hinkley's _Theoretical Statistics_
> give beautiful discussion to this effect, but not in so few words.

Here is a summary of the responses:

>From Norm Phillips,
Peter Bouman,
Stephen Smith,

McCullagh & Nelder 2nd Ed. p.8

>From Richard J Traub

According to a posting last year on the Riskanal list, the answer is:

All Models Are Wrong But Some Are Useful
(note Caps are as in the quote)

George E.P. Box

Page 202 of "Robustness is the Strategy of Scientific Model Building" in
Robustness in Statistics. eds., R.L. Launer and G.N. Wilkinson, 1979, Academic

>From Rachel Fewster
Jean Adams
Jerry W. Lewis

I believe the quote you're interested in is from G.E.P. Box, 1976:
Science and Statistics. J. American Statistical Association, 71,

>From Eric Gibons

Another good quote is by John Tukey (Annals of Math Stat, 1962, V33, p1-67)

"Far better an approximate answer to the right question,
which is often vague,
than an exact answer to the wrong question,
which can always be made precise."


This message was distributed by To unsubscribe
send e-mail to with the BODY of the
message: unsubscribe s-news