The sciences, or subfields within each science, divide into those which have kept a focus on How Big and those which have not. No geomorphologist, for example, would rest satisfied that "there exists" an effect of rainfall on the height of the land: she wants quantitative estimates of the rate of mechanical denudation . . . [continues]
Related documents in Prudentia's archives:
[Continued from above]
- The Cult of Statistical Significance: Preface and table of contents
- "The Cult of Statistical Significance", Stephen Ziliak & DNM, JSM 2009, Section on Statistical Education: 2302-19. (This is the 2nd-most downloaded article on StatLit.)
On its influence in the US Supreme Court decision regarding statistical significance
"Brief for Statistics Experts Professors Deirdre M. McCloskey and Stephen T. Ziliak in Support of Respondent" before the US Supreme Court, Matrixx v Siracusano, Nov 12, 2010, No. 09-1156, oral argument, Jan 10, 2011
"Making a Stat Less Significant," Carl Bialik, Wall Street Journal, 2 Apr. 2011
"A Statistical Test Gets Its Closeup, Wall Street Journal, 1 Apr. 2011
Supreme Court Decision delivered by Justice Sotomayor, 22 March 2011
"'Statistical Significance' and the US Supreme Court: Ziliak-McCloskey
See also McCloskey's published articles on "The Rhetoric of Significance Testing and Econometrics"
The Unreasonable Ineffectiveness of Fisherian 'Tests' in Biology, and Especially in Medicine," DNM & Stephen Ziliak, Biological Theory 4(1) 2009, 44-53.
- "Science is judgment, not only calculation: a reply to Aris Spanos's review of The cult of statistical significance" (Stephen Ziliak & DNM, Dec. 2008, Erasmus Journal for Economics and Philosophy)
- "Signifying Nothing: Reply to Hoover and Siegler" (DNM & Stephen Ziliak, Apr. 2007)
- "Why Economics Is on the Wrong Track" (DNM, 2006)
- "The Trouble with Mathematics and Statistics in Economics" (DNM, 2005)
- "Econowannabes" (DNM)
Order information, The Cult of Statistical Significance
The sciences, or subfields within each science, divide into those which have kept a focus on How Big and those which have not. No geomorphologist, for example, would rest satisfied that "there exists" an effect of rainfall on the height of the land: she wants quantitative estimates of the rate of mechanical denudation . . . continues
in millimeters per century. No physicist is much interested in the "statistical significance" at conventional levels between exact IA calculations as against pole approximations of the electromagnetic form factor at high values of four-momentum transfer squared: he wants to see the quantitative difference in a simulation and argue that it matters for the science. No historian would be comfortable with a claim that German migration to the United States "was a factor" in the election of 1860: she would want to know how much. What matters to science is oomph, every time. Unhappily, in many fields of science the matter of How Much has been lost, commonly by a confusion between actual scientific measurement on the one hand and philosophical absolutes on the other. One counterexample to Goldbach's Conjecture (that every even number can be expressed as the sum of two primes: 20 = 13 + 7) would suffice to kill it for good in the Department of Mathematics. Yet it would still go on being useful to engineers devising computer locks, since no counterexample has been found for numbers up into the billions. Existence, arbitrary statistical significance, philosophical possibilities uncalibrated to the sizes of important effects in the world are useless for science. Yet in medical science, in population biology, in much of sociology, political science, psychology, and economics, in parts of literary study, there reigns the spirit of the Mathematics or Philosophy Departments (appropriate in their own fields of absolutes). The result has been a catastrophe for such sciences, or former sciences. The solution is simple: get back to seeking oomph. It would be wrong, of course, to abandon math or statistics. But they need every time to be put into a context of How Much, as they are in chemistry, in most biology, in history, and in engineering science.