Willcox, Walter Francis

Copyright notice

This article Walter Francis Willcox was adapted from an original article by Margo J. Anderson, which appeared in StatProb: The Encyclopedia Sponsored by Statistics and Probability Societies. The original article ([http://statprob.com/encyclopedia/WalterFrancisWillcox.html StatProb Source], Local Files: pdf | tex) is copyrighted by the author(s), the article has been donated to Encyclopedia of Mathematics, and its further issues are under Creative Commons Attribution Share-Alike License'. All pages from StatProb are contained in the Category StatProb.

Walter Francis WILLCOX

b. 22 March 1861 - d. 29 October 1964

Summary. Willcox, demographer and statistician, founded the statistical research office in the U.S. Census Office, and was a major innovator in demographic analysis and apportionment theory and methodology in the United States.

Walter F. Willcox was born in Reading, Massachusetts, and received Bachelor's and Master's degrees from Amherst College in 1884 and 1888. He went on to attend Columbia University and he continued his studies in Germany in the late 1880s. There he encountered statistical methods and ideas, and shifted his earlier interests in law and philosophy to data-inspired empirical social research. He received a PhD from Columbia University in 1891 after completing a thesis on divorce (published as The Divorce Problem: A Study in Statistics, (Studies in History, Economics and Public Law, New York: Columbia University Press: 1897).

Willcox took a position as Professor of Economics and Statistics at Cornell in 1891, served as dean from 1902 to 1907, and remained at Cornell until he retired to emeritus status in 1931. His major contributions to statistics were in the realm of demography, apportionment methodology, and the development of the federal statistical system. From 1899 to 1902 he served as Chief Statistician for the Twelfth Census of the United States and in that capacity encouraged the hiring of PhD trained statisticians to the positions of special agents in charge of the technical development of censustaking. Those appointees included Allyn Young, Wesley Mitchell, Joseph Hill, Carroll Doten, William Rossiter, Warren Persons, E. Dana Durand, all of whom served as Presidents of the American Statistical Association in later years. During his tenure at the Census Bureau, he encouraged the production and publication of special analytic reports on census methods and census results. These were published as Supplementary Analysis and Derivative Tables: Twelfth Census of the United States (Washington, GPO, 1906) and provided the prototype for the development in to the Census Monograph Series. Willcox himself continued his relationship with the Census Bureau after returning to Cornell in 1902; he served as a special agent from 1902 on. He was President of the American Statistical Association in 1912, the American Economic Association in 1915, and a long time member of the ASA-AEA Census Advisory Committee which began after World War I. He was elected President of the International Statistical Institute in 1947.

As a founding father of the field of demography (and the Population Association of America) in the United States, Willcox encouraged the development of data on birth, fertility, marriage and divorce, mortality, migration and population composition. He developed methods of analysis, including a ratio of children under five to women of childbearing age which could be use to calculate fertility rates in the absence of birth registration data. And he had a long term interest in congressional apportionment methodology, advocating the method of major fractions from the turn of the century on. Willcox played a major role in the controversies over the census apportionment method in the 1920s, when Congress refused to reapportion itself because it could not sort out the conflicting criticisms of the quality of the 1920 census, two conflicting formulas for apportionment, and the changing demography -- particularly urbanization -- of the United States. Willcox testified before Congress while in his nineties on these issues, remaining extremely critical of Congress' choice of the method of equal proportion over his method of major fractions. Though he had participated in the development of the legislative compromise that ended the Congressional stalemate over apportionment methods in the late 1920s, he remained critical of the failure of Congress to support equal districting within the states as well as equal apportionment among the states. He was also a lone voice in the wilderness deploring the increasing malapportionment of Congress in the first half of the twentieth century, and was 101 when the United States Supreme Court rectified the situation with the ``one person, one vote" decision of 1962. Willcox died in 1964.

References

[1]	Grossman, David Michael (1973). Professors and Public Service, 1885-1925: A Chapter in the Professionalization of the Social Sciences. Unpublished Ph.D. dissertation, Washington University, St. Louis. \smallskip For his papers see the Walter Willcox Collection, Library of Congress, Washington, DC.
[2]	Willcox, Walter (1897). The Divorce Problem: A Study in Statistics. Studies in History, Economics and Public Law, Columbia University Press, New York.
[3]	Willcox, Walter (1940). Studies in American Demography. Cornell University Press, Ithaca, NY.
[4]	Willcox, Walter (1933). Introduction to the Vital Statistics of the United States, 1900 to 1930. Government Printing Office, Washington, DC.

Reprinted with permission from Christopher Charles Heyde and Eugene William Seneta (Editors), Statisticians of the Centuries, Springer-Verlag Inc., New York, USA.