George Waddel Snedecor


Born: 20 October 1881 in Memphis, Tennessee, USA
Died: 15 February 1974 in Amherst, Massachusetts, USA


George Waddel Snedecor's parents were James George Snedecor and Emily Alston Estes. James, the son of a lawyer, was born in Louisville, Mississippi in 1855 and also became a lawyer. He married Emily on 20 January 1880 and George Waddel, the subject of this biography, was their first child. Because James had poor health, the family moved to an isolated log cabin home in Florida when George was one year old. The family lived there for five years and George's sisters, Elizabeth, Harriet and Ione, and a brother, Estes, were born there. James regained his health and changed his profession, becoming a minister in the Presbyterian Church. From 1887 to 1890 the family lived in Dunedin, Florida but then moved to Alabama where they lived in several different villages where James was a minister at the local church. Two further brothers for George were born in Alabama; Palmer Godden in 1891 and James Gayle in 1894. George had just begun his elementary schooling in Florida before the family moved to Alabama where he completed the rest of his schooling. From 1894, the family lived on a farm near Woodlawn and James served as minister at Woodlawn Presbyterian Church from 1899 to 1903.

George Snedecor attended Alabama Polytechnic Institute in Auburn for two years beginning in 1899. He then spent two years, 1901 and 1902, teaching at the Presbyterian Preparatory School in Salem, Alabama. During the last of these years teaching, another brother was born, Philip Alston in February 1902. In 1903 the family moved to Tuscaloosa, Alabama, and Snedecor continued his studies at the University of Alabama to be near his family. He majored in mathematics and physics, and graduated with a B.S. in 1905. He was then appointed as an instructor at Selma Military Academy in 1905, moving after two years to Austin College, Sherman, Texas, where he taught mathematics and Greek. It was while teaching at Austin College in Sherman that he met Gertrude Douglas Crosier whose mother was a dormitory matron at the College; they were married in Sherman on 29 December 1908. Let us record at this point that George and Gertrude Snedecor had two sons, Edward Crosier (born in 1914) and James George (born in 1917). In 1910 Snedecor left Austin College to take up an appointment in Ann Arbour as a Graduate Assistant in Physics at the University of Michigan. He also studied for a Master's Degree in physics and he was awarded the degree in 1913.

In 1913 Snedecor was appointed as an Assistant Professor of Mathematics at Iowa State College and in the following year he was promoted to Associate Professor. Herbert David writes [14]:-

He soon found himself involved in helping research workers, especially in agriculture, in the design and analysis of their experiments. Fostering this activity was to be his life's mission.
In session 1914-15 Iowa State College introduced new courses "Probability and Least Squares" and "Mathematics as Applied to Social and Economic Problems." Five years later the two courses had become "Statistical Method of Interpreting Experimental Data" and "Biometric Methods of Interpreting Agricultural Data". Certainly up to this time Snedecor had only been involved in teaching statistics and had no publications in the topic. The change appears to be due to Henry Wallace, an agricultural graduate of Iowa State College, who gave a series of ten Saturday afternoon lectures to agricultural and biological research workers in 1924. [Henry A Wallace (1888-1965) may be better known as Vice-President of the United States in 1941-45 when Franklin D Roosevelt was President.] Snedecor was in the audience and he collaborated with Wallace to produce a 47-page booklet based on Wallace's lectures. Entitled Correlation and Machine Calculation, this became Snedecor's first publication. The authors wrote in the Preface:-
The rapid extension during recent years of the ideas of simple correlation has imposed their use upon many scientists not trained in the mathematical theory underlying them. The present trend in all biological sciences, as well as in economics and psychology, is still further to extend the use of correlation, broadening its scope to include the associations among more than two variables. One object of this bulletin is to present in simple un-technical language some explanation of the meaning and uses of the various correlation coefficients, simple partial and multiple. The second and principal object of the bulletin is to set forth explicit directions for the use of the usual commercial forms of calculating machines ... . in finding correlation coefficients or related constants.
Oscar Kempthorne [27] explains the importance of Snedecor's approach to statistics:-
Snedecor was almost unique in the U.S. and even in the world in recognizing the nature of one of the major 20th century revolutions or evolutions, the recognition that interpretation of data is a remarkably difficult activity requiring integration of mathematics and some logic of analogy. Snedecor recognized that one could not merely talk about the problem from a purely philosophical viewpoint; the question is not what one should do on the basis of a philosophy of knowledge obtained from untenable axioms - but what one should do here and now with the current given question ... . How does one interact usefully with the observable world ... ?
This approach is clearly visible in the book which has, more than anything else, become his most significant achievement, namely Statistical Methods Applied to Experiments in Agriculture and Biology (1937). Here are some extracts from the Preface which show Snedecor's aims:-
The beginner in experimentation too often finds himself supplied with a pair of elaborate mechanisms. In the one hand is a mass of data demanding simplification and interpretation, while in the other is a complex statistical methodology said to be necessary to research. How shall the two be geared together? Since the data can be only insufficiently utilised without statistical method, and since method is futile until applied to data, it seems strange that greater effort has not been made to unite the two. For those of some experience there are adequate texts and journal articles. It is the novice to whose needs this book is directed. ... The only mathematics used in this book is arithmetic, supplemented by enough symbolism to make the exposition intelligible. ... The easiest ideas are put first, and only one new concept is presented at a time. ... Numerous examples form an indispensable part of the presentation.
In 1927 the Mathematics Statistical Service was founded at Iowa State College; it was led by Snedecor and his colleague A E Brandt. Tragedy struck the family, however, in 1930 when their fifteen year old son Edward died from spinal meningitis. Academically things were going exceptionally well with Snedecor's student Gertrude Cox completing the first Master's Thesis on statistics at Iowa State in 1931 and, in September of the same year, Snedecor was given charge of the computing services. Also in 1931 he was promoted to Professor of Mathematics. In 1933 the Statistical Laboratory was founded with Snedecor as its director [14]:-
The laboratory's functions are described in the College Catalogue for 1934-1935 under five headings: Research; Statistical Counsel; Teaching; Computation Service; and Calculating Machines. It is explained that the laboratory is not a department of instruction, but that members of its staff devote part of their time to teaching statistics in the Mathematics Department. Snedecor, Brandt and Cox were the initial faculty members of the Statistical Laboratory. Their teaching on the theory side was supplemented by other members of the Mathematics Department.
Snedecor retired from his role in the Statistical Laboratory on 30 June 1947. On the occasion of his retirement, the President of Iowa State College said (see [10]):-
Professor Snedecor may relinquish his administrative duties with the knowledge and satisfaction that he has developed one of the most important research activities in the nation today. For this fine work he has the gratitude and thanks of every scientist.
Retirement from the Statistical Laboratory did not mean that he was about to leave the College for he had already put in much effort towards establishing a Department of Statistics at Iowa State College and, on 1 July 1947, the Department came into being. Snedecor was appointed professor in the Department of Statistics, serving until 1958. In 1950 he published another important book Everyday Statistics - facts and fallacies. Tippett writes in his review [37]:-
Professor Snedecor has in mind the layman and so he introduces each bit of statistics in terms of some everyday problem, and explains the ideas underlying the statistical approach in everyday terms. And what a fascinating set of problems they are! Teachers and lecturers will value this feature of the book. The exposition is unhurried and the working of the illustrative examples carried through step by step, with full explanation of the meaning of each step. The author takes the reader on a series of excursions of rather exciting discovery.
Despite this praise, Tippett had his worries:-
... the reviewer has doubts that he cannot still. Although "no mathematics beyond elementary algebra is required" and "the attempt is made to present the logic of the science with only so much mathematical symbolism as is necessary for clarity," the "lay reader" has to learn, and learn quickly, a formidable amount of what he must regard as jargon.
Certainly the book did not prove anything like as popular as Statistical Methods.

Leaving Ames after he retired from Iowa State College in 1958, Snedecor and his wife moved to San Diego, California. Although he was now 77 years old he still wanted to give of his skills and in 1959 he took up a consulting position at the United States Navy Electronics Laboratory. Indeed he had a great deal to give to the Laboratory and he collaborated, particularly with E R Anderson, on analysing data from experiments in oceanography and underwater acoustics. In 1963 Snedecor left his consulting position at the Navy Electronics Laboratory so that he could look after his wife who had become seriously ill. By 1965 Snedecor's own health was also failing and he took a heavy blow when his wife had a stroke in June 1966 falling into a coma which she never came out of; she died in September 1966. Snedecor himself suffered a stroke in February 1968 and was not expected to recover. He did, however, make a partial recovery and was well enough to live for two years from 1971 to 1973 with his son James in Amherst. He spent the final year of his life in the Amherst Nursing Home.

Snedecor received many honours from Iowa State College including an honorary D.Sc. in 1958 and, in 1969, the building at the College which houses the Statistical Laboratory and the Department of Statistics was named Snedecor Hall. He received many other honours: he was elected to the American Association for the Advancement of Science in 1933, to the American Statistical Association in 1939, to the Institute of Mathematical Statistics in 1942, to the International Statistical Institute in 1950, an Honorary Fellow of the British Royal Statistical Society in 1954, and an Honorary Life Member of the International Biometrics Society in 1971. He served as President of the American Statistical Association in 1947 and he was awarded the Samuel S Wilks Memorial Medal in 1970. The citation for this Medal reads:-

To George W Snedecor for his pioneer contributions in the development and use of statistical methods, including applications of experimental design to research investigations, and for introducing several generations of statisticians and research workers to the subject statistics through teaching and the six editions of his world-renowned book, 'Statistical Methods'.
This was not the last edition of Statistical Methods, however, for in 1989 an eighth edition appeared. It states in the Preface:-
The first edition of this book was published in 1937 with George W Snedecor as the sole author. Snedecor asked William G Cochran to do the revisions for the sixth edition, and Cochran was listed as the second author of the sixth and seventh editions. The present edition was prepared by several members of the Department of Statistics at Iowa State University. The revisions were guided by the principle that the work should remain the work of its original authors; thus, much of the material remains as previously published.
Finally we mention the tribute paid to him by the publication of the book Statistical papers in honor of George W Snedecor (1972). Ted Bancroft edited the volume and wrote in the Preface:-
This volume is presented as a tribute to George Waddel Snedecor, founder and first director of the Statistical Laboratory at Iowa State University. Its contributors include friends, former students, and former colleagues of Professor Snedecor - able statisticians who were asked to select their own topics and provide their own scientific refereeing. ... we believe that this collection will be of interest to statisticians and scientists who know Professor Snedecor personally and to those who have become acquainted with him through various editions of his outstanding book, 'Statistical methods'. Together, these groups should include nearly every statistician and many scientists in the world, for the impact of George Snedecor's statistical work on many scientific investigations in various fields is indeed worldwide.

Article by: J J O'Connor and E F Robertson

November 2010
MacTutor History of Mathematics
[http://www-history.mcs.st-andrews.ac.uk/Biographies/Snedecor.html]