Mike Bennett

Michael Antony (Mike) Bennett (February 21, 1934 - November 17, 2016) was one of the longest serving actuarial science faculty members at Waterloo, having served from September 1968 until his retirement in July 1996.

Mike, who was born in West Yorkshire, graduated from the University of Nottingham in the UK in 1957. By his own admission, he arrived in Canada by ship later that year and began work as an Actuarial Student at Sun Life in Montreal.  While at Sun Life, he met Peter Ryall, and followed Peter to the University of Waterloo as its second full-time actuarial faculty member in 1968. He obtained his FSA (Fellow of the Society of Actuaries) and FCIA (Fellow of the Canadian Institute of Actuaries) designations in 1970.

Liked and respected by all who knew him (faculty and students alike), Mike was a selfless contributor to actuarial science at Waterloo during his long tenure. Although there was no official position as Associate Chair for Actuarial Science in the early years, Mike served tirelessly in that role, and continued to provide valuable service thereafter. He was noteworthy for his considerable teaching load as well as for his countless hours performing administrative service, including in particular his role as undergraduate advisor for the actuarial students. One of the most impressive aspects of Mike's personality was the fact that he did not seek accolades for his substantial contributions to Waterloo Actuarial Science in particular, and Mathematics in general (he was Chair of the Mathematics Faculty Council from the mid 1980's until his retirement). To be more precise, he was instrumental in assisting in the considerable growth of actuarial science at Waterloo through a variety of avenues including course development.

Mike treated all with respect, including in particular younger faculty and the many students whom he advised and mentored. In addition to being an outstanding teacher, he took a special interest in all of his students. This was epitomized by the fact that he typically knew the names of all of the people enrolled in his classes by the end of his first or second lecture. More generally, he had a unique manner of making all feel that they were important. He enjoyed the interaction with his students in his role as undergraduate advisor.

Mike professional interests were primarily in the area of Pensions, and he was a Pension Consulting Actuary on the side. He also served the community in a variety of roles, and he enjoyed golf and soccer as well.

A devout family man, Mike had one sister (Enid Poprosky) and was married at the time of his death to June Whalen Piitz. He was predeceased by his first wife Gwenneth Bennett (Mercer). He had four children, namely Michael, Geoffrey, David, and Julie, as well as numerous stepsons, grandchildren, and step-great-grandchildren.

Mike was truly one of the founders of actuarial science at Waterloo, and the tremendous success of our program is due in no small part to the efforts and contributions of Mike. As an institution, we owe him a great deal.

In Memoriam
V.P Godambe

Vidyadhar Prabakhar Godambe, who died June 9, 2016, is recognized as a pioneer in the foundations of inference in survey sampling.

He is known for formulating and developing a theory of estimating equations. His research contributions, and the fervour with which he pursued the answers to fundamental questions, attracted many other researchers and students to work in the foundations of inference.

Vidyadhar Godambe was born June 1, 1926 in Pune, in the state of Maharashtra in India. He was the second born and the only son in a family of four children. His paternal grandfather was a doctor. He was educated at the Nutan Marathi Vidyalaya, a leading school in Pune, and at Fergusson College for his BSc in mathematics. He was awarded an MSc degree from Bombay University in 1950, and the PhD in 1958 from the University of London. Following a year as Senior Research Fellow at the Indian Statistical Institute in Calcutta, he became Professor and Head of the Statistics Department at Science College in Nagpur, and later held the same post at the Institute of Science, Bombay. In 1964, he left India for North America, his first position being at the Dominion Bureau of Statistics, now Statistics Canada. After visiting appointments at Johns Hopkins University and the University of Michigan, he joined the University of Waterloo in 1967.

While employed as a government statistician before undertaking his PhD, Godambe published the path-breaking paper, “A unified theory of sampling from finite populations”, published in the Journal of the Royal Statistical Society in 1955. This paper provided a theoretical framework for the problem of estimating a survey population total from a probability sample of a subset of the population. This framework led to a result that today we might call “disruptive”, namely that in terms of the optimality criteria in use at the time, there was no best estimator in the class of linear estimators now referred to as the “Godambe class”. Thus the need for new ways of evaluating sampling strategies was established. The framework is still in use; the 1955 paper led to substantial work by Godambe and others on new optimality criteria, and on prescriptions for choosing sampling designs and estimators under various kinds of knowledge of the population.

The late 1950s and early 1960s were a time of re-examination of the foundations of inference in terms of “principles”, by leading statisticians such as G. A. Barnard, A. Birnbaum, D. R. Cox, D. A. S. Fraser and D. A. Sprott. It became clear to Godambe that his formulation of the survey estimation problem brought into sharp relief an apparent contradiction: the likelihood and conditionality principles appeared to be in conflict with “design based estimation”, namely the practice of estimation based on the randomization in the sampling design. Beginning with his 1966 JRSS paper, “A new approach to sampling from finite populations”, he wrote several papers on the riddle of the role of randomized sampling in survey inference, particularly in the presence of a statistical model for the survey responses. His 1982 paper, “Estimation in survey sampling: robustness and optimality”, in the Journal of the American Statistical Association, proposed a resolution of the problem, relating the robustness of design-based inference to the treatment of nuisance parameters in a more traditional statistical model framework. However, in the same year and the same journal, he published the example known as “Godambe’s paradox”. The wide variety of responses to the paradox show that the tension between the principles of inference and the role of randomization persists beyond survey inference, to the very foundations of statistics.

Godambe’s work in the mid-nineteen sixties on the foundations of survey sampling inference attracted attention to the subject, and he provided further impetus by proposing an international conference to bring together survey statisticians and researchers in the foundations of statistics, many of whom would be new to survey sampling. This conference, “New Developments in Survey Sampling”, took place in 1968 at Chapel Hill, North Carolina.

Having arrived at the University of Waterloo, together with David A. Sprott he organized another international symposium on the Foundations of Statistical Inference, which took place in the spring of 1970. He remained in Waterloo thereafter, although he also spent the winter months in India in later years, and kept in touch with colleagues at the University of Pune.

In parallel with his work on survey sampling, he was also making contributions to estimation theory. In 1960 he published the note, “An optimum property of regular maximum likelihood estimation”, in which he defined the notion of an unbiased estimating equation. He introduced an optimality criterion for choosing among estimating functions, and showed that in the one-dimensional parametric case, the maximum likelihood estimating function (and equation) were optimal. There existed already an optimality theory for estimators, based primarily on their properties for very large samples. Godambe’s focus on the estimating function rather than the estimator allowed him from his perspective to formulate and prove optimality results without reference to asymptotics. Subsequent work by Godambe and others developed estimating function methodology into an established framework for estimation.

Godambe’s follow-up work on estimating functions included his 1976 Biometrika paper where what is now known as “Godambe information” was introduced. His application of optimality and information to estimation in stochastic processes had a substantial impact on work in that field.

In his sixth decade of statistical research, Godambe with his collaborators explored the improvement of confidence intervals based on estimating functions, in survey sampling and in time series analysis. Ever drawn to the foundations of inference, he once again took up his long-term interests in causality, and the concept of information in statistics.

Godambe was a Fellow of the Institute of Mathematical Statistics, a Fellow of the American Statistical Association and an Honorary Member of both the Statistical Society of Canada and the International Indian Statistical Association. He was a Platinum Jubilee Lecturer of the 1988 Indian Science Congress, and in 1987 was awarded the Gold Medal of the Statistical Society of Canada. In 2002 he was elected a Fellow of the Royal Society of Canada.

Godambe’s lifelong dedication to research and teaching did not prevent him from being devoted to his

extended family in India and North America, and a good friend to colleagues around the world and members of his community. His enthusiasm for ideas and his infectious laughter will be greatly missed.

-Mary Thompson

Acknowledgements: An article on which this one is based was first requested by the Royal Statistical Society some years ago. Some portions are adapted from an Appendix (by M. Thompson) to the 2006 biography, Philosopher-Statistician: Vidyadhar Godambe, by Chintamani Deshmukh.

In Memoriam
Jim Kalbfleisch

Jim Kalbfleisch passed away Sunday, April 23, 2017 at his home in Waterloo. Jim served as Chair of the Department of Statistics (now Statistics and Actuarial Science) from 1975-1979. He was Dean of the Faculty of Mathematics from 1986 - 1989, leaving that position to serve as Associate Provost, Academic Affairs from 1990-1993 and then Vice-President Academic and Provost from 1993 – 2000.

The position of provost was created in 1987 (prior to that, the job was known as Vice-President, Academic) and was described as the University's "chief operating officer," covering responsibilities that at many other institutions would be handled by an array of vice-presidents; academic, administration, and finance (indeed, after Kalbfleisch announced his retirement, some of the provost's duties were transferred to a new position of vice-president, administration and finance held by Dennis Huber). Kalbfleisch served as provost under James Downey and David Johnston, drafting budgets, presenting them to finance committees and the board of governors, and conducted meetings with staff and faculty leaders about policies and working relationships. He also prepared enrolment and construction plans and negotiated them with the provincial government, chaired the weekly dean's council meetings, and made final decisions on a multitude of business and personnel issues, all the while managing the University through salary rollbacks, massive early retirements, enrolment expansion and changes in the terms of employment for faculty members.

During his time as the Vice-President Academic and Provost, the university was experiencing a time of enrolment expansion and funding cuts that led to the special early retirement program (SERP) in 1996. His leadership, solid judgment and unwavering commitment to the University kept Waterloo on an even keel through a historically challenging period for the province's post-secondary sector.  In addition, Jim helped lay the groundwork for how the university accommodated its share of the "double cohort" of Ontario high school graduates in 2003 as the province phased out its fifth year of high school.

Jim did undergraduate studies at University of Toronto. He received his Master’s degree in 1964 and PhD in Mathematics in 1966 from the University of Waterloo. His PhD thesis entitled “Chromatic Graphs and Ramsey's Theorem" was supervised by Ralph Stanton. Jim began teaching in the Department of Mathematics in 1964, and when the Faculty of Mathematics was formed in 1967 with Dave Sprott in dual roles as Dean of the Faculty and Chair of the Department of Statistics, Jim was appointed Associate Chair of the Department. He took on many responsibilities in the new Department, and guided it through its early years as new faculty members were hired and courses were mounted. At the end of Dave Sprott’s term in 1975, Jim became Department Chair and served until 1979. During those formative years, the department developed internationally recognized programs of research and teaching in both statistics and actuarial science.

Jim was an outstanding teacher, known for his clear exposition. He was also the author of the Springer-Verlag books Probability and Statistical Inference: Volume 1: Probability and Volume 2: Statistical Inference, first published in 1979, and republished in 1985. These books developed from course notes for Math 233 (which became Stat 230 and Stat 231 when the course was divided into two terms), and were the required texts for the department’s introductory courses for many years. In the preface to these books, he points out that “the content of Volume 2 is unusual for an introductory text. The importance of the probability model is emphasized, and general techniques are presented for deriving suitable estimates, intervals, and tests from the likelihood function.” He was an early advocate for using computers in the teaching of Statistics, involving APL in much of his teaching. The basic ideas in Jim’s books and his upper year course notes still provide much of the foundation for undergraduate statistics as taught today at Waterloo.

Jim retired in early 2001, having spent 26 of his 34 years as a faculty member in major administrative posts. Among the many tributes from his colleagues at his retirement was this one from then-President David Johnston: "No one has shown more dedicated to the university than Jim Kalbfleisch." 

Former President James Downey told the audience at Jim's retirement party that his choice of Kalbfleisch as provost in the summer of 1993 was "the crowning decision of my career as a president" at three Canadian universities.

Then-Associate Provost Catharine Scott called him "the finest man this institution has ever seen."

Jim was elected a Fellow of the American Statistical Association in 1975, and served as President of the Statistical Society of Canada in 1984. On his retirement from Waterloo, he was named Provost Emeritus. He also served as President and Treasurer of the UW Retirees Association. He was an avid bridge player, an active member of the KW Weavers and Spinners Guild, and enjoyed knitting and working in stained glass.

"He was critically important in developing the University of Waterloo and in working to maintain a sense of civility during some difficult times," remembers Kenneth McLaughlin. "His was a truly extraordinary career and he was a formative influence."

There are two scholarships for incoming students that bear his name: the James G. Kalbfleisch National Scholarship in the Faculty of Mathematics, and the James Kalbfleisch Entrance Scholarship at the University level.

By Brandon Sweet, Steve Brown, Jerry Lawless and Mary Thompson.

In Memoriam
David Sprott
David A. Sprott (Distinguished Professor Emeritus 1930-2013)

David Arthur Sprott, one of the pioneers and leaders of statistics in Canada, died on December 13, 2013 in Waterloo, ON. He was 83.

Born and raised in Toronto, David Sprott completed BA, MA and PhD degrees at the University of Toronto in 1952, 1953 and 1955, respectively. His PhD thesis, written under the supervision of Professor Ralph Stanton, was on the combinatorics and geometry of balanced incomplete block designs. Following his PhD, he received an NRC postdoctoral fellowship to study as a Research Assistant in Genetics at the Galton Laboratory at the University of London under L.S. Penrose, (1955-1956). In 1956 he returned to Canada as Biogeneticist and Clinical Teacher in the Department of Psychology at the University of Toronto (1956-1958). He joined the University of Waterloo in 1958 as an Associate Professor having been recruited by Professor Stanton who had come to Waterloo a year earlier, the year the University was founded.

Two important events took place before coming to Waterloo. While at the Galton Laboratory, he met Sir Ronald A. Fisher and became more acquainted with some of his work in statistical inference. This began a train of thought that led to his view of statistics and to a decidedly Fisherian approach to inference that guided much of David's work throughout his career. The second event occurred through his association with the Department of Psychology at the University of Toronto. There he met his future wife, Muriel Vogel (later Vogel-Sprott). Muriel also moved to the University of Waterloo in 1958 and in time became a distinguished faculty member of its Department of Psychology. David and Muriel had two children, Anne and Jane, and were lifelong partners until 2009, when Muriel passed away.

David Sprott had a profound influence on the direction of statistics, actuarial science and more broadly the mathematical and computing sciences at the University of Waterloo. He became a full professor in the Department of Mathematics in 1961 and led the statistics group from the very beginning of the University. He served as Chair of the newly created Department of Statistics from 1967 to 1975. He also served as the first Dean of the newly founded Faculty of Mathematics in 1967 until 1972. As Chair of Statistics, his objective was to establish an international presence in statistical inference and its applications. In this endeavour, he placed great emphasis on the teachings and ideas of R. A. Fisher, and emphasized the central role of the likelihood function and fiducial inference in statistics. This was a different direction than what was common at the time. Particularly the ideas of likelihood-based inference have had a substantial impact on the profession and the role of statistics in science. He was quick to realize the importance of the computer in the context of statistical analysis. The Department at Waterloo developed its character during the period when David was Chair. Several graduates of Waterloo were enticed back to the Department and hires both junior and senior gave breadth to the Department's activities. In time, Waterloo became very strong in the theory and applications of statistical inference, biostatistics, industrial statistics (experimental designs, quality control and productivity), actuarial science, and time series.

As Dean of Mathematics, David also saw the importance of computer science as a discipline and as a component of the new Faculty. Departments of Computer Science were only just beginning at that stage and the development of the Department at Waterloo was a key aspect of his tenure as Dean. There were, of course, some in the more traditional branches of mathematics who doubted the academic potential of computer science, seeing it as more of a technical resource than an important academic discipline, but the strong support of then Dean Sprott was key in promoting this crucial aspect of the Faculty's activities in the early days.

He was an outstanding teacher in the true sense of the word. His style did not appeal to all, but to many of his students, he was inspirational. He was obviously very keen on the subject matter and the ideas that he was presenting and he concentrated on the general and philosophical aspects of inference. He was not kind to the Neyman-Pearson approach with many examples at his command to illustrate its weaknesses. He worked foundational discussions to every course, and taught over a broad spectrum of the curriculum. David was never one to mince words and would say in colourful language what he thought. His interview with Mary Thompson that appeared in Liaison (Vol. 3, No. 2, February 1989) gives an excellent glimpse of this style.

David Sprott made many important methodological and applied contributions to statistics. The main research focus was on methods based on the likelihood function. He studied many types of likelihoods, including joint, marginal, conditional, profile and integrated likelihoods. One guiding principle was that inferences such as confidence intervals should reflect the shape of the relevant likelihood. From early days, he was an avid proponent of examining the course of the likelihood function as one aspect of statistical inference. He had particular interest in how best to deal with large numbers of parameters within likelihood inference and worked on methods of marginalization, integration and conditioning to provide valid inferences for the parameters of interest. Throughout his career, he had a very keen interest in applications of the methods to other areas, including genetics, physics, chemistry, psychology and biostatistics. He regularly collaborated with scientists in these  fields. His book Statistical Inference in Science (Springer, 2000) gives an excellent summary of his views on statistical inference and its role in scientific investigations. It contains a large number of applications to illustrate his approaches in depth, and as in much of his work, the focus is decidedly Fisherian in flavour with an emphasis on the likelihood and significance tests and a focus on interesting aspects of inductive inference. This book illustrates the flavour of his many publications, most of which centered on the use of likelihood and related methods in the analysis of real applied problems. His work contributed greatly to the outstanding reputation of the University of Waterloo in statistics and to the reputation of Canadian statistics more generally.

In 1985, David decided to take advantage of a phased retirement opportunity atWaterloo which allowed him to reduce his load to 50%. This was in part to spend the winters in Guanajuato, Mexico, where he and his wife purchased a handsome hacienda home in the small town of Marfil near Guanajuato. After some time, he initiated a collaboration with the Center for Research in Mathematics (known as CIMAT for its Spanish name) and became affiliated with its Statistics Department. The formal relationship began with a Chair of Excellence granted to him by the National Council of Science and Technology of Mexico in 1993. At CIMAT, he taught several courses in statistical inference (in Spanish) and supervised several PhD and master students in statistics. His presence there also led to conferences and workshops on statistics and regular visits of eminent statisticians to CIMAT. His involvement at CIMAT contributed greatly to the development of the field of statistics at CIMAT and in Mexico more generally.

David Sprott's contributions to statistics were recognized with many awards, including Fellow of the American Statistical Association, Fellow of the Institute of Mathematical Statistics and Elected Member of the International Statistical Institute. In 1975, he was elected a Fellow of the Royal Society of Canada. He received the Gold Medal, the highest award of the Statistical Society of Canada in 1988, and was subsequently awarded the distinction of Honorary Member of the SSC. In 1997, he was awarded the title Distinguished Professor Emeritus by the University of Waterloo.

David Sprott had other passions, including wine and cider making as well as cooking, with certain well-spiced specialties to his credit. He loved nature, and shared his rustic cabin in Muskoka with a multitude of mice and occasionally a colleague. Later, he purchased a wooded property near Waterloo where he could be found walking on fine summer days. He was a skilled canoeist, and could demonstrate how to right one that had capsized. But it was photography that rivaled statistics as his passion. He was an accomplished photographer, who early on had an outstanding portfolio of photographs of birds. Later his interest moved to photography of flowers and small plants with sharp impressions against the sun. His photographic contributions were recognized with Fellowship in the Royal Photographic Society. Of all his honours, he was perhaps proudest of this.

David Sprott died at his home in Waterloo on December 13, 2013. His many contributions will long be felt and remembered. A memorial tribute to his life and contributions was held at the University of Waterloo on March 28, 2014.

In Memoriam