Prodyot Kumar Bhattacharya
Prodyot Kumar Bhattacharya passed away March 9, 2018, at his home in Davis, California. He was professor emeritus at the University of California at Davis and contributed to the field of statistics during a career that spanned more than 50 years.
PK, as he was called by many colleagues and friends, entered Presidency College to earn his bachelor’s degree in statistics and ultimately received his master’s degree and PhD under the supervision of H.K. Nandi from Calcutta University. In 1960, he traveled to the United States and held postdoctoral positions at The University of North Carolina at Chapel Hill and Stanford University. After a brief period at the Indian Statistical Institute (ISI) in Calcutta, he returned permanently to the US in 1965 upon accepting a position at the University of Arizona. He spent sabbatical terms at the University of Minnesota, ISI, and Massachusetts Institute of Technology. In 1980, he left Arizona to help establish the UC Davis Division of Statistics, where he remained until his retirement in 1994. He supervised PhD students, served on the editorial boards of Sankhya and the Annals of Statistics, and, in 2016, published Theory and Methods of Statistics, a book for advanced graduate students and research statisticians, with his co-author, Prabir Burman.
PK’s early seminal work, published in the Annals of Mathematical Statistics in 1966, proposed a uniformly superior estimator for the mean of a multivariate normal vector under unknown variance and generalized loss function, an important expansion on Charles Stein’s surprising result showing inadmissibility of the ordinary least squares estimator in dimensions exceeding two. Throughout his career, PK maintained special interest in nonparametric estimation functions and change-point analysis, an area that led to demonstrating the large sample behavior of the maximum likelihood estimator of an unknown change-point through a Brownian motion process with drift. His research was motivated by unusual problems across a spectrum of disciplines. Of particular note, his collaboration in a cosmological application led to a nonparametric inference method for a regression model having errors with infinite variance and a truncated response, an approach that reconciles the red shift effect of a light source in an ever-expanding universe and the truncation arising from the low luminosity of distant objects. The method allows analysis and interpretation of complex astronomical data, such as those collected by the Hubble Space Telescope.
PK was born on September 30, 1930, in Calcutta, India. The fourth of six children, he lost his mother and younger sister when he was a young boy. Despite hardship at an early age, he found joy in the books he discovered at the local Boys’ Own Library. He developed a special fondness for Bengali and English poetry and, for the rest of his life, could recite from memory the verses that moved him during his school days. He loved popular and classical Indian and western music, all kinds of food and spirits, and traveling to all corners of the world. He was happiest when sharing these lifelong passions with others, whether it was setting out his favorite selection of cheeses, introducing his grandchildren to classic movies, or attending an opera performance in San Francisco or New York.
PK left an indelible mark on science and the lives he touched through his intellect, humor, generosity, and spirit of adventure. He is survived by his wife of 54 years, Srilekha; his daughters, Suparna Jain and Aparna Anderson; and his grandchildren, Arjun and Anjali Jain and Anil and Mira Anderson.
Eun Sul Lee
“The man departs—there remains his shadow.”
-Chinese aphorism
Eun Sul Lee, age 83, died peacefully with his family surrounding him on April 2, 2018, at the Mirabella retirement community in Portland, Oregon. The retired professor was a scholar; teacher and mentor; author; origami master; true gentleman; and devoted husband, father, and grandfather of three.
Born in Gongju, Korea, in 1934, Eun Sul lived through the end of the Japanese occupation (1945) and the Korean War (1950–1953) before he went to college at Seoul National University, where he studied sociology. After college, he worked as a translator at the Christian Children’s Fund in Seoul, where he met his future wife, Chong Mahn. They were engaged in Seoul before they both moved to the United States to attend graduate school—he at the University of Kentucky (for an MA in statistics) and she at the Pittsburgh Theological Seminary. Later, he earned his PhD in experimental statistics and sociology from North Carolina State University.
Eun Sul began his academic career at the University of Texas School of Public Health in Houston in 1969 and remained there for 36 years, until his retirement. While at UT, he advised master’s and doctoral students and taught classes in demography, biostatistics, survey sampling and community health assessment, planning, and evaluation. He also participated in numerous funded research projects and served on review committees for the National Cancer Institute; National Heart, Lung, & Blood Institute; and National Institute of Mental Health (NIMH). He also consulted extensively with the NIMH and the World Health Organization.
While on leave from UT from 1994 to 1996, he developed and chaired the department of preventive medicine and public health at Ajou University Medical School in Suwon, Korea. He also taught and consulted at several universities in Asia, including Seoul National University, Yonsei University, Gunma University, and the Hokkaido University.
Upon his retirement in 2005, Eun Sul and Chong Mahn moved to Portland, Oregon, where he became an adjunct professor in the department of public health and preventive medicine at the Oregon Health & Science University (OHSU). He also provided statistical consulting services for the Mental Health Services Research Program at the Portland Veteran Affairs Medical Center.
Eun Sul participated in the writing of more than 100 journal articles and scholarly reports, authored three textbooks (one in Korean and two in English), and wrote a memoir titled Dreaming with One Eye Open for his children and grandchildren. In his memoir, he chronicled his family history, childhood in Korea, life during wartime, move to the United States, and, later in life, coming to terms with his father’s legacy.
His father, Lee Chul Ha, died in 1936 after being imprisoned by the Japanese for protesting colonial rule in Korea. Eun Sul grew up knowing little about his father. While on sabbatical in Korea in 1992, he discovered his father was one of the leaders of the nationalist resistance movement in his hometown and was active in a student revolutionary group in Seoul. When these findings were made known to the South Korean government, his father was honored with a Patriot’s Medal in 1993 and his grave was moved to the National Cemetery shortly thereafter.
Eun Sul is survived by his wife, Chong Mahn Lee; daughter, Margaret Juhae Lee; son-in-law, Steven Paul Francis Olson; son, Edward Tongju Lee; daughter-in-law, Amy Lee Lacks; and three grandchildren, Owen Sung Ya Lee Olson, Dahlia Mina Lee, and Kiana Yong Mi Lee Olson.
A private ceremony will be held. Memorial donations may be made to the Oregon Health & Science University Foundation.
Herman Rubin
Written by Anirban DasGupta
Herman Rubin, professor of statistics and mathematics at Purdue University, passed away in West Lafayette, Indiana, on April 23, 2018; he was 91.
Herman was among the last remaining great polymaths of the 20th century. To all who knew him or had heard about him, he was an inexplicable outlier in numerous ways. His unique ability to understand a new problem and arrive at the answer almost instantly baffled even the wittiest mathematicians. He never forgot a fact or a theorem or a proof. He would solve a complete stranger’s problem without expecting co-authorship or anything in return. He would fight for someone who opposed him at every step. He would stand on his principles with the last drop of blood in his body. Herman’s death marks the end of a unique era following World War II that saw the emergence of a group of supremely talented statisticians who would mold the foundations of the subject for decades to come.
Herman earned his PhD from The University of Chicago at a young age; he was a student of Paul Halmos. After a stint at the Cowles Commission, he formed a productive intellectual affinity with Ted Anderson, Charles Stein, and Ingram Olkin; at that same time, he also became professionally close to David Blackwell and Meyer Girshick. With Ted Anderson, he wrote two phenomenal papers on fundamental multivariate analysis that worked out the fixed sample and asymptotic distribution theory of MLEs in factor analysis models and structural equation models. These results have entered into all standard multivariate analysis and econometrics texts and have remained there for more than a half century. Herman’s most famous and classic contribution to inference is the widely used and fundamental idea of monotone likelihood ratio families. Anyone who has ever taken a course on testing of hypotheses knows how fundamental the idea and results in the 1956 paper with Samuel Karlin were. It was this work that led to Karlin’s hugely influential TP2 and variation diminishing families with shadows of Isaac Schoenberg and Bill Studden lurking in the background.
Following this period, Herman made novel entries into various aspects of probability and asymptotics. With J. Sethuraman, he did theory of moderate deviations. With Herman Chernoff, he attacked the then novel problem of estimating locations of singularities, and how, precisely, the asymptotics were new. With Prakasa Rao as his student, he got into the problem of cube root asymptotics for monotone densities. With C. R. Rao, he gave the classic Rao-Rubin characterization theorem. And, to many, the crown of the jewel was the invention of the Stratonovich integral.
Herman really did enjoy particular problems, as long as they were not mundane particular problems. Classic examples are his papers with Rick Vitale that show sets of independent events characterize an underlying probability measure, degeneracies aside; his work with Jeesen Chen and Burgess Davis on how nonuniform a uniform sample can look to the eye; his work with Tom Sellke on roots of smooth characteristic functions; his work on the Bayesian formulation of quality control with Meyer Girshick; the hilariously bizarre but hard problem of estimating a rational mean; his papers with Andrew Rukhin on the positive normal mean; his work on the notorious Binomial N problem; and his work on Bayesian robustness of frequentist nonparametric tests. There are others. Herman never thought of who would cite or read a result; if he wanted to solve a problem, he did.
Herman was probably one of the lifelong Bayesians, but a purely axiomatic one. He really did take most of the Savagian theory and axioms literally; he expanded on them, though later. An expansion was published in Statistics and Decisions (to my knowledge, with extremely active help from Jim Berger). He would not budge an inch from his conviction that the likelihood and prior are inseparable. He would refuse to discuss what an appropriate loss function was; he would insist you ask the client. He would nevertheless want to see the full risk function of a procedure and would study Bayes through the lens of Bayes risk, and even exclusively Bayes risk, namely the double integral. On asymptotic behaviors of procedures, he did not appear to care for second-order terms. He has shown his concern for only calculating a limit time and again. A glorious example of this is his work with J. Sethuraman on efficiency defined through Bayes risks; this was so novel it entered into the classic asymptotic text of Robert Serfling. He came back to it many years later in joint work with Kai-Sheng Song in an Annals of Statistics article.
In certain ways, Herman came across as self-contradictory. He would publicly say only Bayes procedures should be used. But he would oppose the use of a single prior with all his teeth. He would be technically interested in robustness of traditional frequentist procedures, although he would portray them as coming out of wrong formulations. Well-known examples are his well-cited papers with Joe Gastwirth on the performance of the t-test under dependence. He did not have the personal desire to burn the midnight oil on writing a comprehensive review of some area, but he would be an invaluable asset if someone was writing one such. An example is his review of infinitely divisible distributions with Arup Bose (and this writer). An all-time classic is his text Equivalents of the Axiom of Choice, jointly written with his wife, Jean Rubin. Jim Berger thanks Herman profusely in the preface of his classic Springer book on decision theory and Bayesian analysis; Charles Stein acknowledges Herman and Herbert Robbins in his first shrinkage paper.
There was a fairly long period when nearly every paper written in Herman’s home department had his contributions in it. He never asked for or got credit for them. He defined the term scholar in its literal dictionary sense. With the passing of Herman Rubin, a shining beacon of knowledge and wisdom is gone. Herman was an absolute and consummate master of simulation, characteristic functions, and infinitely divisible distributions. He kept to himself a mountain of facts and results on these and other topics. There was never a person who did not respect Herman Rubin’s brain; even Paul Erdös did. He was an inaugural fellow of the American Mathematical Society and a fellow of the Institute of Mathematical Statistics.
Herman had sophisticated taste in music and literature. He was often seen at classical concerts and operas. He helped mathematical causes financially. Herman was probably one of the few people who could work out the NY Times crossword puzzle on any day in about an hour. Herman is survived by his son, Arthur, and daughter, Leonore.
Leave a Reply