A
Literary Saloon
&
Site of Review.

Trying to meet all your book preview and review needs.

Contents:

Main

the Best

the Rest

Review Index

Links

to e-mail us:

the complete review - mathematics

Statistics on the Table

by
Stephen M. Stigler

general information | review summaries | our review | links | about the author

- Return to top of the page -

Our Assessment:

B : often fascinating episodes from the history of statistics -- but also fairly specialized.

See our review for fuller assessment.

  From the Reviews:

• "Although Stigler has written a general introduction and each essay can stand alone, preambles to the five thematic parts of the collection might have provided a welcome wide-angle perspective. Fortunately, even at the chapter level, Stigler skillfully keeps his attention -- and ours -- on the forest even when stopping to marvel at the trees." - Valerie M. Chase, American Scientist
  
  
• "Mr. Stigler's writing is at times technical, and may sometimes make for difficult reading. But his treatment of the topic is always entertaining." - The Economist

Please note that these ratings solely represent the complete review's biased interpretation and subjective opinion of the actual reviews and do not claim to accurately reflect or represent the views of the reviewers. Similarly the illustrative quotes chosen here are merely those the complete review subjectively believes represent the tenor and judgment of the review as a whole. We acknowledge (and remind and warn you) that they may, in fact, be entirely unrepresentative of the actual reviews by any other measure.

- Return to top of the page -

The complete review's Review:

       Stephen Stigler's collection of 22 essays (one written together with William H. Kruskal) offers a wide variety of stories from the history of statistics. It may not seem the most promising of fields, but Stigler ably relates episodes of discovery and interesting examples of statistical applications. Despite the real-world significance of much that is discussed, it must be acknowledged that this is a somewhat obscure field and that many of the figures are far from household names. However, Stigler does an excellent job of placing statisticians and their contributions in the proper context and light in this work which is as much historical as statistical.
       Most of these essays were originally written for a strictly professional audience (though many were extensively revised for this book), and it is unlikely the layman will have previously come across them. Fortunately, few of them are overly technical -- Stigler is as concerned with describing the discovery, applications, and disagreements regarding statistical innovations and methods as he is with the strict maths. (A number of the essays do, however, address statistical concepts of some complexity, and a familiarity with such basic concepts as that of "least squares" is almost a prerequisite for a reasonable understanding of the statistical issues being addressed.)
       The essays are grouped in five sections, centered around Statistics and Social Science, Galtonian Ideas, Some Seventeenth Century Explorers, Questions of Discovery, and Questions of Standards. A number of statisticians figure prominently, including Karl Pearson, from whom the title of the collection is taken, William Stanley Jevons, and Francis Galton. The topics are often fairly arcane, but the application and significance of statistics is far-reaching, as Stigler makes clear.
       Among the episodes related in the first section is the controversy surrounding a study by Pearson on the influence of parental alcoholism on children, a provocative piece of analysis that was attacked from many quarters. In the second section a number of Galtonian contributions are discussed -- from fingerprint identification to Stochastic Simulation in the Nineteenth Century. The third section turns the clock back farther, looking at the work of statisticians of the seventeenth century, a useful (though again somewhat specialized) historical overview.
       It is the last two sections, covering questions of discovery and of standards that will probably be of most interest to general audiences. The question of eponymous practice -- the naming of an epoch or a law or theory or a unit of measurement after a scientist -- is raised in several of the pieces. Among the most entertaining is that proposing Stigler's Law of Eponymy, which claims that: "No scientific discovery is named after its original discoverer" (which apparently holds true for this law as well). Stigler also offers a statistics detective story in Who Discovered Baye's Theorem ? (with the understanding that it is obvious it was not Baye -- see Stigler's Law), using statistical methods to reach his conclusions.
       In the section on Questions of Standards Stigler presents the interesting problem of The Trial of the Pyx, a ceremony "to ascertain that coinage issued by the Mint met the Crown's specifications." Here, as throughout the collection, Stigler combines history with statistical problems and questions, a blend he manages very well.
       Stigler writes engagingly and clearly, and most of the pieces in the volume manage to be both informative and quite entertaining. Many of the topics are fairly obscure, but Stigler manages to convey them well, using historical context to enliven what many may consider dry statistics. The significance and reach of statistics, over the past centuries, is also clearly demonstrated here. Stigler's fastidious research impresses, as does his far-reaching curiosity. His enthusiasm for the subjects (statistics, the history of statistics, and the statisticians) also comes across, and he does his best to share it with his readers.
       Not overly technical (though a few of the essays do include statistical analysis beyond the most basic level), this book is fairly specialized. However, anyone interested in the history of science or in mathematics and statistics in general should enjoy it. An impressive collection.

- Return to top of the page -

Links:

• Harvard University Press publicity page

• Faculty page at the University of Chicago

• See Index of books dealing with Mathematics

- Return to top of the page -

About the Author:

       Stephen M. Stigler is a Professor of Statistics at the University of Chicago

- Return to top of the page -

© 1999-2021 the complete review

Main | the New | the Best | the Rest | Review Index | Links