Skip to main content

Walter Smith Obituary

March 24, 2023

Walter Smith Obituary

March 24, 2023

W. Smith Obituary

Published by The News & Observer in March 19, 2023.

Walter Laws Smith

November 12, 1926 – March 6, 2023

Chapel Hill, North Carolina – Walter “Wally” Laws Smith died March 6, 2023 at Carolina Meadows in Chapel Hill, North Carolina. He was 96 years old. Walter was preceded in death by his wife of 69 years, Mary Ramsden Smith. Walter is survived by his daughter Caroline Smith of Albuquerque, New Mexico, by his son Simon Smith of Chapel Hill, North Carolina, and by his sisters Betty Haggerty and Julia Grahame in England.

Walter was born in London, England in 1926 to parents Thomas and Dorothy Smith. In 1947, he graduated with an honors degree in Mathematics from the University of Cambridge where he was a member of Pembroke College. From 1947 to 1950, he served as a lieutenant in the Instructor Branch of the Britannic Royal Navy. He was stationed first at Fort Halstead in Kent and later at HMS Sea Eagle in Londonderry, Northern Ireland. It was during his time at Fort Halstead that he developed an interest in statistics.

In September of 1950, he married Mary Ramsden Redman, whom he had met in 1944 while attending school in Maidstone, Kent. After leaving the navy in 1950, he returned to Cambridge for graduate school, and in 1953 he was awarded a PhD in Mathematical Statistics for his thesis “Stochastic Sequences of Events”. During his time as a graduate student, in addition to his studies, he developed a keen interest in magic; in the summers he and Mary performed in touring magic shows with the student Pentacle Club. Walter achieved Associateship of the Inner Magic Circle in 1952, an elite status awarded to a limited number of magicians.

In 1954, Walter and Mary moved to Chapel Hill, North Carolina, where Walter became an assistant professor of statistics at the university. Between 1955 and 1958, he also taught at the University of Florida at Gainesville, at North Carolina State University in Raleigh, at the University of California at Berkeley, and at the University of Cambridge. Eventually, in 1958 he and Mary decided to live permanently in Chapel Hill. From then on, he remained a faculty member of UNC’s Statistics department until his retirement in 1994, serving as department chairman from 1981-1986. His field of expertise was probability theory, specifically queues, the subject of the book he co-authored in 1961.

In 1960, Walter was awarded Cambridge University’s prestigious Adams Prize for his submission “Contributions to Renewal Theory”. In 1974, he was awarded a Guggenheim Fellowship for his sabbatical leave in Cambridge, where he was a Sir Winston Churchill Overseas Fellow at Churchill College. He was known as an outstanding lecturer and a witty raconteur. In addition to being invited as a plenary speaker at major statistical conferences across the world, he was also sought out to give after-dinner speeches to entertain attendees.

In the 1960s and 70s, Walter was active in local amateur drama. His major roles included Bottom in two different Playmakers productions of A Midsummer Night’s Dream, Ko-Ko (The Lord High Executioner of Titipu) in The Mikado in productions with the Playmakers and later with the Durham Savoyards, John Wellington Wells in The Sorcerer and Major-General Stanley in The Pirates of Penzance, both with the Durham Savoyards, Alfred P. Doolittle in My Fair Lady for Duke Hoof ‘n Horn, Dylan Thomas in Dylan with Duke Summer Theater, and Socrates in Maxwell Anderson’s Barefoot in Athens.

From the early to mid 1980s, Walter was very interested in using the new home computers to type mathematical documents. He created the technical word processing software packages QWERTY and DAISY, which led to the development of his son’s technical word processor EXP.

In his retirement, Walter enjoyed reading, painting oil pictures, playing the piano, listening to his enormous collection of classical music, tinkering with his computers, and making annual trips to England and France. In December 2009, Walter and Mary moved into the Carolina Meadows retirement community in Chapel Hill, where he became an active member of the film club. His final lectures were given as part of Carolina Meadows University on the topic of the Dreyfus Affair.

It was Walter’s wish that he be cremated and that there be no memorial service or funeral. For anyone who wishes to remember him with a donation, two charities he supported are the Chatham Outreach Alliance food pantry in Pittsboro ( and the Carolina Meadows Foundation

Bahadur lecture

March 24, 2023

Bahadur lecture at IISA 2023 meeting

March 24, 2023

Bahadur lecture

Prof. Budhiraja will be giving the plenary Bahadur lecture at the forthcoming 2023 IISA meeting at the Colorado School of Mines in Golder, CO.
You can check the event website here:

Ragu Raj Bahadur

Ragu Raj Bahadur was born on April 30, 1924 in Delhi, India. After completing his undergraduate education in the University of Delhi, he secured his Ph.D. in statistics from the University of North Carolina, Chapel Hill in 1950, under the guidance of Herbert Robbins. In the 1950s he served as a Professor at ISI, Calcutta, and from 1961 onwards, he was a Professor of Statistics at the University of Chicago, where he retired in 1992 and passed away as a Professor Emeritus on July 7, 1997, at the young age of 73.

Bahadur was a fellow of the American Academy of Arts and Sciences, the Institute of Mathematical Statistics, the International Statistical Institute, the Indian National Sciences Academy and the Indian Academy of Sciences. He was an excellent lecturer and the 1974 Wald Lecturer of the IMS and served as the President of the IMS in 1974-75.

Bahadur made several foundational and seminal contributions to statistics. His papers are extremely well written and transparent. His paper on `On Fisher’s bound for asymptotic variances’ provides an elegant proof of the fact that in the absence of regularity conditions the Fisher information bound for the asymptotic variance of CAN estimate of a parameter may be violated on a set of parameter values having Lebesgue measure zero. In connection with his work on Bahadur efficiency he developed in depth large deviation analysis of the log-likelihood ratio statistic. One of his most cited paper is the paper bearing the title “A note on quantiles in large samples” in Ann. Math. Statist. 37, 577–580, 1966, where he obtained an almost sure first order approximation for the sample quantile. This work was later refined by Jayant Ghosh and Jack Kiefer. It is now known as the Bahadur-Ghosh-Kiefer representation. Bahadur’s work with T.W. Anderson on solving binary classification problems with applications to statistical classification and engineering is known as the Anderson-Bahadur algorithm.

Steve Stigler, the Ernest De Witt Burton Distinguished Service Professor of Statistics at the University of Chicago, says that “Raj was one of the architects of the modern theory of mathematical statistics. His work, which was characterized by a singular depth and elegance, changed the way statisticians think about statistical information at a fundamental level. People from all over the world made pilgrimages to see him.” To honor his legacy, the IISA has instituted Bahadur Lecture Series since 2017.

Past Bahadur Lecturers were:

  • Soumendra Lahiri (2022, Bengaluru)
  • Arup Bose (2019, Mumbai)
  • Alexander Belloni (2018, Gainesville)
  • Jay Sethuraman (2017, Hyderabad)

(By Hira Lal Koul)

DataFest 2023

March 8, 2023

ASA DataFest at Duke 2023

March 8, 2023

DataFest 2023

ASA DataFest at Duke 2023 is organized by the Department of Statistical Science at Duke University and will take place Friday March 24th through March 26th, 2023. The last day to register is March 10th.

DataFest is a data analysis competition where teams of up to five students attack a large, complex, and surprise data set over a weekend. Your job is to represent your school by finding and communicating insights into these data. The teams that impress the judges will win prizes as well as glory for their school. Everyone will have a wonderful experience, lots of food, and fun!

The event is open to all Undergraduate and Master’s students, regardless of level of programming experience. In previous years, students in introductory STAN courses have won awards and prizes. Additionally, in anticipation of the event weekend, Duke’s Center for Data and Visualization Sciences will host pre-event workshops. See the DataFest website for more details:

Whether you form a team or wish to be assigned to a team, registration is open! You can sign up (and read more about DataFest) here:

SDSS position

January 10, 2023

Joint position with the School of Data Science and Society

January 10, 2023

Data Science Position

The School of Data Science and Society (SDSS) and the Statistics & Operations Research Department (STOR) are hiring a joint position. This joint hire will have its tenure home in the STOR Department but will hold a half-time appointment at SDSS and contribute to their teaching and research mission as well.

The new hire will be helping to build undergraduate and graduate programs with a strong quantitative core as well as many interdisciplinary options. As a part of this overarching initiative to deepen and expand research and teaching related to data science, applications are being invited at Assistant or Associate Professor rank with a starting date of July 01, 2023.

The STOR department is organized around four areas: theoretical and applied statistics; probability; stochastic modeling; and optimization. Faculty in the department conduct fundamental research in these areas and have many collaborations with other parts of UNC including health care, medicine, public health and environmental sciences.

The ideal candidate for this position would be someone with primary expertise in one of the STOR department’s core areas, at the intersection with data science including machine learning, and potential for developing significant collaborations with the SDSS. The successful candidate will be expected to direct an independent research program supported by extramural funding, to participate in data science activities and to teach at the undergraduate and graduate levels through the STOR department and SDSS.

We will begin considering candidates after January 15, 2023, and will continue accepting applications until the position is filled. Questions should be directed to the Search Committee at

Link to the job application

RTG lectures by Resnick

January 4, 2023

Mini course by Sidney Resnick

January 4, 2023

RTG mini course

Sidney Resnick from Cornell visiting us from January 7th to January 28th. He will be giving a series of six lectures on the topic of:

Multivariate Power Laws and Preferential Attachment Modeling

This is part of the lecture series funded by the NSF RTG grant DMS 2134107.

Abstract: In one-dimension, heavy tails or power-laws are easily understood to represent Pareto like behavior where data plotted on a log-log scale looks roughly linear. The generalization to higher dimensions is not always obvious and the infinite variety of dependence possibilities can be daunting. Multivariate regular variation of measures is a clean, flexible and clear way forward. A variety of mathematical and statistical techniques guide a user.

Network modeling of social networks using preferential attachment presents other challenges. Models can be difficult to analyze and only occasionally do simulations from these models leave a comfortable impression that simulation matches reality. One glaring discrepancy is “reciprocity”, meaning the percentage of directed edges that link to nodes (network users) in both directions. (You like me and I like you. You reference my paper and I reference yours.) Real data exhibits higher reciprocity compared to what is given by simulations from traditional preferential attachment.

In- and out-degree sequence data for many social networks marginally exhibit the expected straight line power law behavior and preferential attachment models theoretically predict this both marginally and in the two-dimensional sense. We can add reciprocity to the model by assuming something like “when I connect to you, you flip a coin to decide if you want to connect with me.” This and its generalizations corrects the empirical under-prediction of reciprocity and introduces the feature that asymptotically the limit measure of regular variation concentrates on a line. This means large values of in- and out-degree tend to always be present simultaneously, a property called “asymptotic full dependence”. Without reciprocity, preferential attachment leads to in- and out-degree having a limit measure of regular variation that concentrates on the full positive quadrant meaning that a large value of either in- or out-degree can be associated with a variety of values in the other.

Schedule: The lectures will be held in Hanes 125 at the following dates and times:

  • TTh (Jan 10, 12): 4:15-5:30 pm
  • Tue (Jan 17): 4:45-6:00 pm
  • Th (Jan 19): 4:15-5:30 pm
  • TTh (Jan 24, 26): 4:15-5:30 pm

STOR students may earn credit by registering for STOR 893.

Pre-requisites: foundation in probability and statistics at the graduate level.

Bio: Sidney Resnick is the Lee Teng-Hui Professor in Engineering Emeritus at Cornell. Resnick joined the Cornell faculty in 1987 after nine years at Colorado State University, six years at Stanford University, and two years at the Technion, in Haifa, Israel. He received his Ph.D. from Purdue University in 1970. His interests center in applied probability and cross the boundary into statistics. Past foci include modeling queues, storage facilities, extremes, data and social networks, risk estimation and tail estimation. Resnick is a Fellow of the Institute of Mathematical Statistics, a founding associate editor of Annals of Applied Probability, and past associate editor of Journal of Applied Probability, Stochastic Processes and their Applications, Stochastic Models, Extremes, The Mathematical Scientist. He has authored or coauthored approximately 190 papers and four books.

RTG postdoc 2023

December 10, 2022

Postdoctoral position in NSF RTG

December 10, 2022

Postdoctoral position

The Department of Statistics and Operations Research invites applications for a three-year postdoctoral fellowship starting July 1, 2023. The position is funded by the Research training grant from the NSF, Networks: Foundations in Probability, Optimization, and Data Sciences.

The position comes with a two-course teaching load per year. The primary responsibility of the postdoctoral fellow will be to develop an independent and vigorous research program with guidance from RTG faculty members. In addition, the postdoctoral fellow will be actively involved in various activities of the RTG including mentoring of undergraduates in research and running of research seminars. Areas of interest include Probability, Optimization, Statistics, Machine Learning, Data Science.

The department and university are committed to diversity, equity and inclusion, advancing the ideals espoused at We welcome applications from candidates who will add to the department’s diversity.

Interested candidates should submit application materials (CV, research statement, two or more letters of recommendations) by January 15, 2023 at

U.S. citizenship or permanent residency required.

Should you need any further information, please contact us via

The University of North Carolina at Chapel Hill is an equal opportunity, affirmative action employer and welcomes all to apply without regard to age, color, disability, gender, gender expression, gender identity, genetic information, national origin, race, religion, sex, sexual orientation or veteran status.

Student Awards

December 5, 2022

2022-2023 Student Awards

December 5, 2022

Student Awards

The department would like to congratulate the following outstanding students.

Walter L. Deemer Excellence in Teaching Award

  • Ackerman, Andrew
  • Kar, Sumit

Excellence in Teaching Assistance and Instruction Award

  • Keefe, Thomas
  • Ozkan, Dilay
  • Panagiotis, Andreu

2022-2023 STOR Dissertation Award

  • Luo, Yiyun

Cambanis-Hoeffding-Nicholson Award
(for outstanding performance in first-year graduate courses and CWEs)

  • Kim, Minji
  • Lee, Seong Jin
  • Liu, Rui

A Celebration in Memory of Ross Leadbetter

November 26, 2022

A Celebration in Memory of Ross Leadbetter

November 26, 2022

Honoring Leadbetter

The Department is organizing a meeting on Saturday, February 25, 2023.
See more information in the event website.


Richard Davis (Columbia University)
Ivette Gomes (Universidade de Lisboa)
Tailen Hsing (University of Michigan)
Steve Marron (University of North Carolina at Chapel Hill)
Thomas Mikosch (University of Copenhagen)
Susan Murphy (Harvard University)
Vladas Pipiras (University of North Carolina at Chapel Hill)
Sid Resnick (Cornell University)
Holger Rootzen (Chalmers University of Technology)
Gennady Samorodnitsky (Cornell University)