Synopses & Reviews
This book provides a selection of pioneering papers or extracts ranging from Pascal (1654) to R.A. Fisher (1930). The authors' annotations put the articles in perspective for the modern reader. A special feature of the book is the large number of translations, nearly all made by the authors. The selected articles vary considerably in difficulty, some requiring only a basic understanding of statistical concepts, whereas others surprise by their early sophistication in classical statistics. There are several reasons for studying the history of statistics: intrinsic interest in how the field of statistics developed, learning from often brilliant ideas and not reinventing the wheel, and livening up general courses in statistics by reference to important contributors. Herbert A. David is Distinguished Professor Emeritus in the Department of Statistics, Iowa State University and served as Department Head from 1972 to 184. He was Editor of Biometric from 1967 to 1972 and President of Biometric Society for 1982-1983. His publications include books on Order Statistics (Wiley 1970, 1981) and The Method of Paired Comparisons (Griffin 1963, 1988). Apart from articles in these two areas he has written on statistical inference, experimental designs, competing risks, and the history of statistics. He received a Ph.D. in statistics from University College London in 1953. A.W.F. Edwards is Reader in Biometry in the University of Cambridge. He was President of the British Region of the Biometric Society in 1992-1994 and is Chairman of the Christiaan Huygens Committee for the History of Statistics of the International Statistical Institute. His publications include the books Likelihood (Cambridge University Press 1972, Johns Hopkins University Press 1992), Foundations of Mathematical Genetics (Cambridge University Press 1977, 2000), and Pascal's Arithmetical Triangle (Griffin 1987). He holds the degrees of Ph.D. and Sc.D. from Cambridge University.
Review
From the reviews: MATHEMATICAL REVIEWS "The book will be a useful addition to libraries and to the collections of those with a special interest in the history of statistical science." CHOICE MAGAZINE "David (Iowa State Univ., Ames) and Edwards (Gonville & Caius College, UK) offer an interesting general historical book treating some aspects of the statistical literature. Because of increasing interest in historical development of probability and statistics, numerous good books and journal papers have appeared that either discuss such developments over a certain period or introduce certain specified and particular topics. This book provides access to some contributions neglected earlier, due either to lack of translation or to renewed interest. The origins of the following statistical concepts are included in the compilation: expectation, test of significance, accuracy of observations, coincidences and the inclusion and exclusion technique, asymptotic relative efficiency, logistic growth curve, goodness-of-fit statistics, distribution of sample variance from a normal population, random walk, estimating a binomial parameter by using likelihood functions, extreme-value theory, tournament outcomes, and confidence limits. Appendixes with short list of collected papers and source books cited; first occurrence of terms commonly used in statistics/probability; useful name and subject indexes; lists of references. The authors have done a great job in taking this task of filling the gaps in the historical introduction into literature of some statistical concepts, and this work will interest all engaged in studying or researching the history of statistics/probability. Highly recommended. Upper-division undergraduates through faculty. SHORT BOOK REVIEWS "Each article is introduced by an essay called 'Comments on...'; these comments are informative, interesting and beautifully written, and contains numerous modern connected references. The production is first class...The collection is fun to browse. Statistics history buffs and browsers should order this book immediately." "If you enjoy the history of statistical and probabilistic ideas, you will enjoy this interesting book. It makes good reading ... . This book is a useful addition to the literature on this increasingly popular subject, and I particularly recommend it to graduate students in statistics. There are many ideas that we think of as essentially modern but that have a long history. This book provides interesting background on quite a few of them." (William E. Strawderman, Journal of the American Statistical Association, 2004) "This book contains 'a selection of pioneering papers or extracts ranging from Pascal (1654) to R. A. Fisher (1930)' ... . The authors present a fascinating collection of articles. The accompanying commentaries are well written, easy to read and very instructive. ... The book may be used as part of a course on the history of statistics or by lecturers wishing to provide a historical context ... . It is also pleasurable recreational reading. I would recommend that libraries purchase a copy." (Paul Northrop, Journal of Applied Statistics, Vol. 30 (1), 2003) "This book contains ... seminal papers, translated into English where necessary, and prefaced by a commentary. In all there are seventeen articles, taken in chronological order, with publication dates spanning nearly three centuries. ... The book will be a useful addition to libraries and to the collections of those with a special interest in the history of statistical science." (C. C. Heyde, Mathematical Reviews, Issue 2002 e)
Review
From the reviews:
MATHEMATICAL REVIEWS
"The book will be a useful addition to libraries and to the collections of those with a special interest in the history of statistical science."
CHOICE MAGAZINE
"David (Iowa State Univ., Ames) and Edwards (Gonville & Caius College, UK) offer an interesting general historical book treating some aspects of the statistical literature. Because of increasing interest in historical development of probability and statistics, numerous good books and journal papers have appeared that either discuss such developments over a certain period or introduce certain specified and particular topics. This book provides access to some contributions neglected earlier, due either to lack of translation or to renewed interest. The origins of the following statistical concepts are included in the compilation: expectation, test of significance, accuracy of observations, coincidences and the inclusion and exclusion technique, asymptotic relative efficiency, logistic growth curve, goodness-of-fit statistics, distribution of sample variance from a normal population, random walk, estimating a binomial parameter by using likelihood functions, extreme-value theory, tournament outcomes, and confidence limits. Appendixes with short list of collected papers and source books cited; first occurrence of terms commonly used in statistics/probability; useful name and subject indexes; lists of references. The authors have done a great job in taking this task of filling the gaps in the historical introduction into literature of some statistical concepts, and this work will interest all engaged in studying or researching the history of statistics/probability. Highly recommended. Upper-division undergraduates through faculty.
SHORT BOOK REVIEWS
"Each article is introduced by an essay called 'Comments on...'; these comments are informative, interesting and beautifully written, and contains numerous modern connected references. The production is first class...The collection is fun to browse. Statistics history buffs and browsers should order this book immediately."
"If you enjoy the history of statistical and probabilistic ideas, you will enjoy this interesting book. It makes good reading ... . This book is a useful addition to the literature on this increasingly popular subject, and I particularly recommend it to graduate students in statistics. There are many ideas that we think of as essentially modern but that have a long history. This book provides interesting background on quite a few of them." (William E. Strawderman, Journal of the American Statistical Association, 2004)
"This book contains 'a selection of pioneering papers or extracts ranging from Pascal (1654) to R. A. Fisher (1930)' ... . The authors present a fascinating collection of articles. The accompanying commentaries are well written, easy to read and very instructive. ... The book may be used as part of a course on the history of statistics or by lecturers wishing to provide a historical context ... . It is also pleasurable recreational reading. I would recommend that libraries purchase a copy." (Paul Northrop, Journal of Applied Statistics, Vol. 30 (1), 2003)
"This book contains ... seminal papers, translated into English where necessary, and prefaced by a commentary. In all there are seventeen articles, taken in chronological order, with publication dates spanning nearly three centuries. ... The book will be a useful addition to libraries and to the collections of those with a special interest in the history of statistical science." (C. C. Heyde, Mathematical Reviews, Issue 2002 e)
Synopsis
Interest in the his tory of statistics has grown substantially in recent years and the subject is now covered by a number of excellent books. S. M. Stigler's The History of Statistics (19S6) gives an overview up to 1900 while Anders Hald's two encyclopedic volumes A History of Probability and Statistics before 1750 and A History of Mathematical Statistics f'T'Om 1750 to 1930, published in 1990 and 1995, provide detailed mathematical discussion of the major contributions up to 1930. Hald's books have re moved Isaac Todhunter's A History of Probability from the pedestal which it occupied for a century and a quarter and rendered Karl Pearson's Lec ture Notes of mainly historical interest themselves. Journal papers have appeared on specific topics, especially in the series "Studies in the History of Probability and Statistics" in Biometrika and in the long sequence of papers in Archive for the History of the Exact Sciences by O. Sheynin. The two volumes of reprinted papers, mostly from Biometrika, issued in 1970 and 1977 have proved particularly valuable. More recently, many important papers published since 1900 have been reprinted with commentaries in the three-volume Breakth'T'Oughs in Statistics (1992-1997). Stigler's Statistics on the Table (1999) provides illuminating vignettes. In addition, specialized books have appeared on particular topics, such as A. I. Dale's A History of Inverse P'T'Obability (1991, 1999) and R. W. Fare brother's Fitting Linear Relationships (199S). The pioneering book on the early period, F. N."
Synopsis
This collection of classic articles in statistics combined with commentary by the editors will be of interest to all serious statisticians.
Table of Contents
The Introduction of the Concept of Expectation--Pascal (1654) * The First Example of a Formal Test of Significance -- Arbuthnott (1712) * Coincidences and the Method of Inclusion and Exclusion -- Montmort (1713), N. Bernoulli (1713), and Moivre (1718) * The Determination of the Accuracy of Observations -- Gauss (1816) * The Introduction of Asymptotic Relative Efficiency -- Laplace (1818) * The Logistic Growth Curve -- Verhulst (1845) * Goodness-of-Fit Statistics: The Distributions in Normal Samples of (a) the Sum of Squares About the Population Mean, (b) the Circular Sum of Squares of Successive Differences, and (c) the Circular Serial Correlation Coeffient -- E. Abbe (1863) * The Distribution of the Sample Variance Under Normality -- Helmert (1876) * The Random Walk and Its Fractal Limiting Form -- Venn (1888) * Estimating a Binomial Parameter Using the Likelihood Function -- Thiele (1889) * Yule's Paradox ("Simpson's Paradox") -- Yule (1903) * Beginnings of Extreme-Value Theory -- Bortkiewicz (1922) and Mises (1923) * The Evaluation of Tournament Outcomes -- Zermelo (1929) * The Origin of Confidence Limits -- Fisher (1930)