Each year, many wait with bated breath to learn the names of the Rock and Roll Hall of Fame inductees. The 2023 inductees include the Spinners, Sheryl Crow, George Michael, Willie Nelson, and my high-school classmate Missy Elliott. If you are a music fan, you may have a list of performers you think belong in the Rock and Roll Hall of Fame.
In this month’s column, I will share nominees for the Statistics and Data Science Hall of Fame based on recommendations from my colleagues on the ASA Board of Directors. I will take this opportunity to also highlight the work of ASA Board members as they drive discovery and inform decisions.
The work of Vladimir Vapnik, especially the Vapnik-Chervonenkis theory of statistical learning, received many nominations. As artificial intelligence and machine learning have entered the public lexicon, it is important to remember the foundational work that makes these advances possible.
One of the nominators for this contribution is Ruixiao Lu, who serves on the board as treasurer and is vice president and head of biostatistics and statistical programming at Alumis. In addition to her work in outcome research, she is a co-inventor of the patent “Algorithms and Methods for Assessing Late Clinical Endpoints in Prostate Cancer” (WO2018148642A1).
“So far as the laws of mathematics refer to reality, they are not certain. And so far as they are certain, they do not refer to reality.” This quote attributed to Albert Einstein appears in a paper by L. Mark Berliner titled “Physical-Statistical Modeling in Geophysics” and serves as a citation for this nomination. The paper describes purely physical models and purely statistical models as the “endpoints of the spectrum of physical-statistical models.” The nomination acknowledges the significant impact of embedding the mathematical model of the laws of physics into the statistical model.
The paper’s nominator is Kate Calder, who is one of the Council of Sections representatives to the ASA Board. She is also the chair of the department of statistics and data science at The University of Texas at Austin. Her research interests are in spatial statistics, Bayesian modeling and computation, and statistical network analysis.
“The best thing to do with missing data is to not have any.” This quote attributed to Gertrude Cox begins The Missing Book, written by Nicholas Tierney and Allison Horst. Methods for handling missing data—missing completely at random, missing at random, and missing not at random—received multiple nominations. On his website, Rod Little provides an overview and highlights relevant research.
Michelle Shardell, who also represents the Council of Sections on the ASA Board, and Jenny Thompson, who is an ASA vice president, nominated this contribution. Shardell is a professor in epidemiology and public health at the University of Maryland School of Medicine. Her interdisciplinary work in biostatistics in aging research includes developing novel statistical methods to handle survival bias and unmeasured confounding in studies of older adults, adapting machine-learning methods in pooled-cohort projects, and treating the use of proxy respondents as a missing-data problem. Thompson is chief of the statistical methods and sample design staff at the US Census Bureau. Her practical and theoretical experience covers all areas of sample survey design, including sample selection, estimation, variance estimation, analysis, statistical data editing, imputation, and quality control.
I’ve shared with you in previous columns that I am mission and vision driven. Our ASA vision looks to a world that relies on statistical thinking to inform decisions, so a nomination recognizing the impact of statistical advances on policy must be included in this list. There are many improved methods for causal inference with observational data that are critical for sound policy. The Urban Institute report titled An Update on the Synthetic Control Method as a Tool to Understand State Policy provides an example of work in this important area.
This nomination came from ASA President-Elect Bonnie Ghosh-Dastidar, who is head of the statistics group and senior statistician at the RAND Corporation. Her areas of policy are health and social and economic well-being.
My dissertation was about survival analysis. Thus, it may come as no surprise that my nominee is none other than Sir David Cox. His 1972 Journal of the Royal Statistical Society, Series B paper in which he developed the Cox proportional hazards model remains foundational and continues to have a far-reaching impact on medicine, science, and engineering nearly 50 years later. I have witnessed the power of the Cox model to inform decisions in my role as deputy director of the Office of Biostatistics in the Center for Drug Evaluation and Research at the Food and Drug Administration.
The Statistics and Data Science Hall of Fame is dynamic, and this column is only a beginning. I welcome your nominations, as our contributions to science and society are numerous. Our goal is to keep adding to our virtual hall of fame.
Leave a Reply