2004 PARZEN PRIZE FOR STATISTICAL INNOVATION

to be awarded by
TEXAS A&M UNIVERSITY DEPARTMENT OF STATISTICS
to
JEROME H. FRIEDMAN

March 1, 2004, 4:00 pm, Chemistry, Room 100

The 2004 EMANUEL AND CAROL PARZEN PRIZE FOR STATISTICAL INNOVATION will be proudly awarded to JEROME H. FRIEDMAN, Professor of Statistics at Stanford University, by the Department of Statistics at Texas A&M University. The prize ceremony is on Monday, March 1, 2004 at 4:00 pm, in the Chemistry Building, Room 100.

Professor Friedman will present a popular lecture entitled

“GRADIENT DIRECTED REGULARIZATION FOR LINEAR REGRESSION AND CLASSIFICATION.”

He will describe his exciting research on linear modeling using novel strategies.

The Parzen Prize for Statistical Innovation is awarded (in April of even numbered years) to North American statisticians who have made outstanding and influential contributions to the development of applicable and innovative statistical methods. The prize has been established to reduce the sparsity of prestigious awards and prizes that recognize outstanding careers in the discipline and profession of statistics. The Parzen Prize for Statistical Innovation is supported by the Emanuel and Carol Parzen Fund which was established as an endowment at the Texas A&M Development Foundation in honor of the 65th birthday on April 21, 1994 of Emanuel Parzen, Distinguished Professor of Statistics at Texas A&M University. Members of the Committee awarding the Prize for 1996 were R. Eubank (Texas A&M), J. Matis (Texas A&M), Marvin Zelen (Harvard), Bradley Efron (Stanford), and Grace Wahba (U of Wisconsin).

The 2004 Emanuel and Carol Prize for Statistical Innovation is awarded to Jerome H. Friedman for his significant innovations in statistical theory that have transformed practice by the creation of influential software, that have significantly influenced modern computational statistics, and that has provided seminal leadership and statistical foundations to research in Data Mining and Knowledge Discovery, Machine Learning and Statistical Learning, and Nonparametric Statistical Methods.

Jerome Friedman is an influential educator, author, journal editor, practitioner, and collaborator in research with many scientists. He has had many outstanding Ph.D. students. He serves the national statistical community with distinction and dedication. Jerome Friedman received his Ph.D. in Physics from the University of California, Berkeley in 1967, and has been a Professor of Statistics at Stanford since 1982.

Professor Friedman is internationally recognized as a world class pioneer in the theory and practice of computational statistics and data science. He has contributed a remarkable array of topics and methodologies to data mining and machine learning, written many expository articles and books (and given an extraordinary number of invited talks) relating data mining and machine learning to statistical foundations, and pioneered and implemented new methodologies including CART, MARS, PRIM, PPR,  MART, and Gradient Boosting.

Emanuel Parzen is Distinguished Professor of Statistics at Texas A&M University. In 1994 he was awarded the Samuel S. Wilks Memorial Medal of the American Statistical Association “for outstanding research in Time Series Analysis, especially for his innovative introduction of reproducing kernel spaces, spectral analysis and spectrum smoothing; for pioneering contributions in quantile and density quantile functions and estimation; for unusually successful and influential textbooks in Probability and Stochastic Processes; for excellent and enthusiastic teaching and dissemination of statistical knowledge; and for a commitment to service on Society Councils, Government Advisory Committees, and Editorial Boards.”