In lieu of an abstract, here is a brief excerpt of the content:

Preface The implied reader of our book is a significance tester, the keeper of numerical things. We want to persuade you of one claim: that William Sealy Gosset (1876–1937)—aka “Student” of Student’s t-test—was right and that his difficult friend, Ronald A. Fisher, though a genius, was wrong. Fit is not the same thing as importance. Statistical significance is not the same thing as scientific finding. R2, t-statistic, p-value, F-test, and all the more sophisticated versions of them in time series and the most advanced statistics are misleading at best. No working scientist today knows much about Gosset, a brewer of Guinness stout and the inventor of a good deal of modern statistics. The scruffy little Gosset, with his tall leather boots and a rucksack on his back, is the heroic underdog in our story. Gosset, we claim, was a great scientist . He took an economic approach to the logic of uncertainty. For over two decades he quietly tried to educate Fisher. But Fisher, our flawed villain , erased from Gosset’s inventions the consciously economic element. We want to bring it back. We lament what could have been in the statistical sciences if only Fisher had cared to understand the full import of Gosset’s insights. Or if only Egon Pearson had had the forceful personality of his father, Karl. Or if only Gosset had been a professor and not a businessman and had been positioned therefore to offset the intellectual capital of Fisher. But we don’t consider the great if mistaken Fisher and his intellectual descendants our enemies. We have learned a great deal from Fisher and his followers, and still do, as many have. We hope you, oh significance tester, will read the book optimistically—with a sense of how “real” significance can transform your science. Biometricians who study AIDS and economists who study growth policy in poor countries are causing damage with a broken statistical instrument. But wait: consider the progress we can make if we fix the instrument. Can so many scientists have been wrong over the eighty years since 1925? Unhappily, yes. The mainstream in science, as any scientist will tell you, is often wrong. Otherwise, come to think of it, science would be complete . Few scientists would make that claim, or would want to. Statistical significance is surely not the only error in modern science, although it has been, as we will show, an exceptionally damaging one. Scientists are often tardy in fixing basic flaws in their sciences despite the presence of better alternatives. Think of the half century it took American geologists to recognize the truth of drifting continents, a theory proposed in 1915 by—of all eminently ignorable people—a German meteorologist. Scientists, after all, are human. What Nietzsche called the “twilight of the idols,” the fear of losing a powerful symbol or god or technology, haunts us all. In statistical fields such as economics, psychology, sociology, and medicine the idol is the test of significance. The alternative, Gossetian way is a uniformly more powerful test, but it has been largely ignored. Unlike the Fisherian idol, Gosset’s approach is a rational guide for decision making and easy to understand. But it has been resisted now for eighty years. Our book also addresses implied readers outside the statistical fields themselves such as intellectual historians and philosophers of science. The history and philosophy of applied statistics took a wrong turn in the 1920s, too. In an admittedly sketchy way—Ziliak himself is working on a book centered on Gosset—we explore the philosophy and tell the history here. We found that the recent historians of statistics, whom we honor in other matters, have not gotten around to Gosset. The historiography of “significance ” is still being importantly shaped by R. A. Fisher himself four decades beyond the grave. It is known among sophisticates that Fisher took pains to historicize his prejudices about statistical methods. Yet his history gave little credit to other people and none to those who in the 1930s developed a decision-theoretic alternative to the Fisherian routine. Since the 1940s most statistical theorists, particularly at the advanced level, have not mentioned Gosset. With the notable exception of Donald MacKenzie, a sociologist and historian of science, scholars have seldom examined Gosset’s published works. And it appears that no one besides the ever-careful Egon S. Pearson (1895–1980) has looked very far into the Gosset archives—and that was in 1937–39 for...

Share