Access the full text.
Sign up today, get DeepDyve free for 14 days.
The discipline of statistics, which barely existed 100 years ago, has made enormous contributions to medical research. Today, virtually every research paper in JAMA uses statistical inventions of the last century, such as randomization, random sampling, hypothesis testing, confidence intervals, and methods that consider the joint influence of many variables on study outcomes. The Lady Tasting Tea is a delightful introduction to the pioneers of 20th-century statistics. In a breezy style, Salsburg describes the careers, contributions, and foibles of people whose names are common eponyms in biomedical articles: Pearson correlation coefficient, Fisher exact test, Student t test. The book is a popular history, not a scholarly treatise. The result is a lively succession of anecdotes filled with humor, academic rivalry, and adventure. Often the writing has the tone of insider gossip. To make the general reader comfortable, there are no mathematical symbols, formulae, or tables. Salsburg has concentrated on relating interesting stories. There are stories of statisticians who fled to Western Europe or the United States to escape poverty, fascism, or communism. The tales of success by women in the field are especially enjoyable. One of the best is about the lady in the book's title. At an afternoon tea in Cambridge in the late 1920s, she claimed that she could taste the difference between tea into which milk had been poured and tea that had been poured into milk. Ronald Aylmer Fisher, the statistician who invented the randomized controlled trial (in agricultural research) devised a randomized trial of the woman's contention on the spot. Fisher later related this experiment in a book but never gave the results of the taste tests; Salsburg reveals the answer. The book does a fine job of telling about the fierce rivalries between the giants of statistics in the early part of the century. Karl Pearson (who changed his first initial from C to K, in admiration of Karl Marx) was the dominant figure in the field when the 20th century began. The brilliant R. A. Fisher, an upstart from an agricultural research station, eventually overshadowed Pearson and took pleasure in diminishing Pearson's accomplishments. In Fisher's later years, he devoted energy to attacking the work of Egon Pearson, the statistician who was Karl's son. The scope of the book includes statistics in economics and other areas. But Salsburg's own background is in the medical uses of statistics, and this is reflected in the book's content. Medical readers may especially enjoy the chapter about Fisher's attacks on the theory that smoking caused lung cancer. In addition to relating many short biographies, Salsburg covers several themes. He does a nice job of describing the growth of statistics as an academic discipline. He explains well how scientific thinking has been influenced by theories about measurement error. He makes the reader aware that there are important debates about the use and meaning of P values and hypothesis tests. In addition, the book gently introduces readers to many concepts, methods, and terms, for example, maximum likelihood and bootstrap methods. The book is less successful in discussing some issues regarding study design and the concept of cause and effect. No matter. Readers who want an in-depth treatment of any topic can look elsewhere. I recommend this book to physicians in training who would like to know about the people who invented the statistical methods that are now taught to medical students and research fellows. I recommend it to any reader who enjoys reading about the history of science.
JAMA – American Medical Association
Published: Sep 12, 2001
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.