{"id":11083,"date":"2013-02-02T05:05:42","date_gmt":"2013-02-02T09:05:42","guid":{"rendered":"http:\/\/etherwave.wordpress.com\/?p=11083"},"modified":"2013-02-02T05:05:42","modified_gmt":"2013-02-02T09:05:42","slug":"r-a-fisher-scientific-method-and-the-tower-of-babel-pt-1","status":"publish","type":"post","link":"https:\/\/rational-action.com\/etherwave\/2013\/02\/02\/r-a-fisher-scientific-method-and-the-tower-of-babel-pt-1\/","title":{"rendered":"R. A. Fisher, Scientific Method, and the Tower of Babel, Pt. 1"},"content":{"rendered":"
\"Fisher1924\"
R. A. Fisher in 1924<\/span><\/figcaption><\/figure>\n

For a paper Chris Donohue and I have been working on, I have been delving into the historiography on statistician and genetic theorist R. A. Fisher (1890-1962). The main thing I was trying to do was to make sense of the last third of Fisher’s touchstone book\u00a0The Genetical Theory of Natural Selection<\/span><\/a>\u00a0<\/em>(1930), which is a protracted eugenic explanation for why civilizations decline. \u00a0When I first got onto this topic, I consulted Greg Radick<\/span><\/a> about it, and he directed me to Stephen Jay Gould’s 1991 essay, “The Smoking Gun of Eugenics” (reprinted in Gould’s\u00a0Dinosaur in a Haystack<\/span><\/a>\u00a0<\/em>collection), in which Gould takes apart both Fisher’s civilizational theory as well as his 1950s-era arguments against claims that smoking leads to cancer.<\/span><\/p>\n

If you’re interested in the specifics of Fisher’s arguments, do read Gould’s essay, or, better still, read the original. \u00a0Suffice it here to say that Gould claims Fisher made bogus arguments on account of his commitment to eugenics (with a similar story for smoking). This is true, as far as it goes, but I wanted to find a “higher-order” explanation for Fisher’s civilizational theory, which would account for why he thought his arguments made sense. \u00a0Fisher, after all, was a famous proponent of methodological rigor, and even\u00a0prima facie\u00a0<\/em>his arguments about civilizational decline were, shall we say, less than rigorous.<\/span><\/p>\n

If you’re interested in my take, you’ll have to wait until 2014 for the edited volume our essay will be in to come out (hooray for academic publishing; if you’re really<\/em> interested, please do contact me<\/span><\/a><\/span> for a draft copy). \u00a0But the general approach I took was to delve into Fisher’s ideas about scientific methodology. \u00a0Below the fold I take a meandering tour through these ideas, and the scattered historiography on them.<\/span><\/p>\n

<\/span><\/p>\n

The main reason I wanted to do some research on Fisher was because of his manuals\u00a0Statistical Methods for Research Workers\u00a0<\/em>(1925), and\u00a0The Design of Experiments\u00a0<\/em>(1935). \u00a0These are pertinent to my work on operations research and decision theory, as well as to my more recent work on agricultural expertise (Fisher wrote both books partially from his experiences helping design agricultural experiments at the Rothamsted Experimental Station, where he worked from 1919 to 1933). \u00a0What is interesting is that neither of these works, nor his later\u00a0Statistical Methods and Scientific Inference\u00a0<\/em>(1956), is a full treatise of scientific methodology.<\/span><\/p>\n

All of these works were, essentially, devoted to inductive reasoning and hypothesis testing. \u00a0For Fisher, the sine qua non\u00a0<\/em>of scientific knowledge was experience. \u00a0The\u00a0security\u00a0<\/em>of that knowledge could be ascertained through the statistical analysis of experimental tests where pertinent variables were controlled either physically or statistically. \u00a0For a recent discussion of Fisher’s commitment to randomization and statistical control of experimental bias, see Nancy S. Hall, “R. A. Fisher and His Advocacy of Randomization,”<\/span><\/a><\/span>\u00a0Journal of the History of Biology\u00a0<\/em>40 (2007): 295-325.<\/span><\/p>\n

\"A
A plan for a controlled agricultural experiment, from: R. A. Fisher and W. A. MacKenzie, \u201cStudies in Crop Variation. II. The Manural Response of Different Potato Varieties,\u201d Journal of Agricultural Science 13 (1923): 311-320.<\/span><\/figcaption><\/figure>\n

Of course, Fisher was aware that there was more to scientific practice than empiricism. \u00a0For him, though, there had to be a definable distinction between speculation and experience, because mistaking mere speculation for scientific knowledge opened the door to dogmatism. \u00a0On this point, I found Harry M. Marks<\/span><\/a><\/span>, “Rigorous Uncertainty: Why RA Fisher is Important,”<\/span><\/a><\/span>\u00a0International Journal of Epidemiology\u00a0<\/em>32 (2003): 932-937 helpful. \u00a0The piece has some very interesting discussion of the ideological significance that Fisher attached to inductivism, particularly its importance to intellectual freedom—a concern that only grew more pronounced in the postwar era (Lysenko and all that).<\/span><\/p>\n

\"Fisher_old\"
An older Fisher<\/span><\/figcaption><\/figure>\n

Marks observes that similar issues were at the core of Fisher’s postwar methodological disputes with statistical theoreticians Jerzy Neyman<\/span><\/a><\/span> (1894-1981) and Abraham Wald<\/span><\/a><\/span> (1902-1950). \u00a0Fisher made the ideological resonance he saw in this issue very explicit in his 1955 paper, “Statistical Methods and Scientific Induction,”<\/span><\/a><\/span>\u00a0Journal of the Royal Statistical Society B\u00a0<\/em>17: 69-78, in which he linked his rivals’ theories to the technologized pragmatism of the Soviet Union and the United States, which privileged “speeding production, or saving money” rather than “drawing correct conclusions”.*<\/span><\/p>\n

Backing up a bit: these postwar methodological disputes were basically extensions of Fisher’s lifelong campaign against “inverse probability,” or, as it is now generally known, Bayesian probability. \u00a0Briefly: in Bayesian probability, an\u00a0a priori\u00a0<\/em>probability distribution (say if there are three possible outcomes to an experiment, one might suppose that each has an equal probability of being the result) is modified following trials. \u00a0For Fisher, whose position is often referred to as “frequentist”, any\u00a0a priori\u00a0<\/em>distribution was an arbitrary imposition on an experimental interpretation, and could not therefore count as scientific knowledge—in trials, any valid\u00a0conclusions had to follow purely from experience.<\/span><\/p>\n

Now, this conflict is one of the<\/em> most celebrated and contentious episodes in the history of statistics. \u00a0In case Fisher’s position seems obviously correct from my brief description, here’s xkcd.com<\/span><\/a><\/span>‘s fine take on the subject:
\n<\/em><\/span><\/p>\n

\"frequentists_vs_bayesians\"<\/span><\/a><\/span><\/p>\n

Unsurprisingly, there is a lot of scattered material on this issue, but your best one-stop-shop is probably\u00a0David Howie’s\u00a0Interpreting Probability<\/span><\/a><\/span>\u00a0<\/em>(2002), which concentrates especially on Fisher’s 1930s-era disputes with Harold Jeffreys<\/span><\/a><\/span> (1891-1989).<\/span><\/p>\n

Now, despite the fact that Fisher was a champion of inductivism, he was also a great deductive statistician. \u00a0For Fisher’s thoughts on deductive reasoning, Marks points us to Fisher’s 1932 lecture, “The Bearing of Genetics on Theories of Evolution,”<\/span><\/a><\/span> in which Fisher extolled his mathematical accomplishments in\u00a0The Genetical Theory of Natural Selection\u00a0<\/em><\/span>reconciling Darwin’s natural selection mechanism with Mendelian genetics.<\/span><\/p>\n

In his lecture, Fisher offered a strikingly different portrait of scientific method from that found in his manuals. \u00a0Invoking the Biblical legend of the Tower of Babel, he observed that a “common metaphor represents the labours of men of\u00a0science as the construction of a gigantic edifice, upon the wings\u00a0and annexes of which workers in different branches of natural\u00a0knowledge are engaged.\u00a0The various methods and techniques in\u00a0which we have been trained correspond to the crafts of the\u00a0different classes of artisans, the stone-cutters, masons, plasterers,\u00a0sculptors, and painters, whose co-operation is needed to produce a\u00a0finished and habitable building.”<\/span><\/p>\n

\"The
The Confusion of Tongues, by Gustave Dor\u00e9 (1865)<\/span><\/figcaption><\/figure>\n

Fisher went on to compare the disaster God inflicted at Babel to the fragmentation of scientific methodology, offering an unusually naturalistic take on how the division of language came to be:<\/span><\/p>\n

We are not told exactly in what manner the confusion of\u00a0tongues originated ; whether by a sudden and miraculous\u00a0transmutation in the word-centre of each individual, he began\u00a0forthwith and, all unconscious of the change, to express his\u00a0ideas in a babbling jargon, meaningless to his fellows ; or\u00a0whether, as the work progressed, groups of workers so concentrated\u00a0their attention upon special parts of the building, and\u00a0on the particular technical problems of their crafts, that they\u00a0gradually came to use words unintelligible outside their own\u00a0little circle ; or, still worse, to use the old words with meanings\u00a0quite unknown to the workers on the floor above, until their old\u00a0common language had been lost irrevocably.<\/span><\/p><\/blockquote>\n

Typically, Fisher cast himself as something of a hero in his lecture, bridging the “unnatural separation of mathematics from biology,” both in his work at Rothamsted, and in his work reconciling genetics with evolution. \u00a0And, importantly, his accomplishment represented a reconciliation of mathematical deduction with inductive science:<\/span><\/p>\n

Deductive and\u00a0inductive reasoning … are the means\u00a0by which alone we can ascertain whether or not a new slab of\u00a0observational fact will fit into its place in our edifice; and the\u00a0mathematical expression of such reasoning is the only effective\u00a0cement which we possess, by which such new facts can be held\u00a0fast as parts of a coherent structure.<\/span><\/p><\/blockquote>\n

Ultimately, though, Fisher’s ideas about the reassembly of the deductive and the inductive into a more unified methodology were never so clearly articulated as his ideas about statistical inference. \u00a0In Pt. 2<\/a>, we look at some scholars’ views of Fisher’s deductivism.<\/span><\/p>\n

—<\/span><\/p>\n

*For more on the relationship between “scientific” knowledge and the problem of limited testing opportunity from an anti-Fisherian perspective, see my post “Decision, Risk, and Values: The Philosophy of Churchman and Ackoff,”<\/span><\/a><\/span> which is a brief excerpt from my book manuscript.<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"

For a paper Chris Donohue and I have been working on, I have been delving into the historiography on statistician and genetic theorist R. A. Fisher (1890-1962). The main thing I was trying to do was to make sense of the last third of Fisher’s touchstone book\u00a0The Genetical Theory of Natural Selection\u00a0(1930), which is a<\/p>\n

Continue Reading… R. A. Fisher, Scientific Method, and the Tower of Babel, Pt. 1<\/span>Continue Reading…<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"nf_dc_page":"","_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[1],"tags":[45,310,577,582,767,1103,1217,1376],"class_list":["post-11083","post","type-post","status-publish","format-standard","hentry","category-uncategorized","tag-abraham-wald","tag-david-howie","tag-harold-jeffreys","tag-harry-marks","tag-jerzy-neyman","tag-nancy-hall","tag-r-a-fisher","tag-stephen-jay-gould"],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/rational-action.com\/etherwave\/wp-json\/wp\/v2\/posts\/11083","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/rational-action.com\/etherwave\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/rational-action.com\/etherwave\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/rational-action.com\/etherwave\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/rational-action.com\/etherwave\/wp-json\/wp\/v2\/comments?post=11083"}],"version-history":[{"count":0,"href":"https:\/\/rational-action.com\/etherwave\/wp-json\/wp\/v2\/posts\/11083\/revisions"}],"wp:attachment":[{"href":"https:\/\/rational-action.com\/etherwave\/wp-json\/wp\/v2\/media?parent=11083"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/rational-action.com\/etherwave\/wp-json\/wp\/v2\/categories?post=11083"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/rational-action.com\/etherwave\/wp-json\/wp\/v2\/tags?post=11083"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}