IN MEMORIAM

Wilfrid J. Dixon

Professor of Biostatistics and Psychiatry, Emeritus

UC Los Angeles

1915-2008

Born on December 13, 1915, in Portland, Oregon, Wilfrid J. Dixon recognized very early in his childhood that numbers fascinated him. One of three sons, he knew it would be his responsibility to finance any advanced studies. So, with his parents’ encouragement, he sold magazines and delivered papers from age 8 to finance his college education. Dixon received his B.A. in mathematics from Oregon State College in 1938, his M.A. in mathematics from the University of Wisconsin in 1939, and his Ph.D. in mathematical statistics from Princeton in 1944 under Samuel S. Wilks. He was on the faculty at the University of Oklahoma (1942-1943), the University of Oregon (1946-1955) and the University of California at Los Angeles (1955-Emeritus since 1986). During 1940-1942 and 1944-1945 he was an operations analyst at Princeton University and on Guam for the Office of Scientific Research and Development.

At UCLA, Dixon had a joint appointment in the Department of Preventive Medicine in the School of Medicine and in the Biostatistics Division in the School of Public Health. He was the first tenured statistician in each of these schools. In addition, Dixon initiated the Biostatistics Division, started its graduate program and served as its first Chief. He organized the Department of Biomathematics in the School of Medicine and served as chair of this department from its inception in 1967 until 1974. In 1973 he was appointed Professor of Psychiatry. As a member of the U.S. – U.S.S.R. Joint Working Group on Computer Software (1974-1980), Dixon served as liaison to the Kolmogorov Laboratory at the University of Moscow.

Many of his over 120 publications result from long-term collaborations in pharmacology, physiology, surgery, neurology, cytology and psychiatry. His commitment to statistical consulting, coupled with his idea to parameterize computer programs in 1960, led to the development of one of the first general statistical software packages, BMD, Biomedical Computer Programs, which has evolved into BMDP Statistical Software.

Dixon organized the Statistical Computing Sections of both the American Statistical Association and the International Statistical Institute. He made major contributions to nonparametric statistics, serial correlation, adaptive (up-and-down) experimental designs, robust statistics and the analysis of incomplete data. He was a Fellow of the American Statistical Association, the Institute of Mathematical Statistics, the Royal Statistical Society and the American Association for the Advancement of Science and received the ASA’s 1992 Wilks Medal. While at the University of Oregon (1951), Dixon coauthored with Frank Massey a first-of-its-kind statistical textbook for non-mathematicians that sold over 300,000 copies.

Will had a broad view of statistics and of the potential of his students’ careers. To quote Dixon: “Statistics is a science in itself, not a branch of mathematics… statistical consulting can be as imaginative and creative as any artistic endeavor.” Dixon’s greatest contribution was his ability to bridge the gap between theory and applications and therefore, bring insight to difficult applied problems.

Jack R. Borsting