Skip to main content
SearchLoginLogin or Signup

The Impact of David Cox’s Work and Leadership on My Research

Published onApr 27, 2023
The Impact of David Cox’s Work and Leadership on My Research

This note is about Sir David Roxbee Cox, arguably one of the most influential statisticians, documenting how his work and leadership have influenced my research and my career development. I am deeply grateful for his exceptional contributions to the community of researchers developing and using statistical methods.

Professor Sir David Roxbee Cox was one of the most influential statisticians and educators. He was internationally renowned for his pioneering and outstanding contributions to the statistical science, especially to the field of survival analysis. According to the Royal Statistical Society (RSS), he was “one of the most important statisticians of the past century” (2020). He was also described as “a giant of statistics" by the Medical Research Council Biostatistics Unit at Cambridge (Downing, 2022). His work and leadership have greatly influenced the research and professional growth of many scholars from various generations, including my own.

The first time I knew David was in my junior year when I was studying mathematical statistics in Zhejiang University in 2013. One day, I came across David’s Journal of the Royal Statistical Society (JRSS) discussion paper on proportional hazards models (Cox, 1972). I was immediately intrigued by the idea of using a conditional likelihood (which was later referred to as the partial likelihood) to eliminate the nuisance parameters from the likelihood function. I felt so excited after reading this paper that I immediately searched his other papers and read his follow-up paper (Cox, 1975) where the notion of partial likelihood is formally introduced and all the large-sample properties are rigorously established. It is these two papers that triggered my interests in academic studies so that I decided to pursue a PhD in statistics after graduation. In a few years, I came to know that his JRSS paper was one of the most-cited statistics papers ever, with approximately 60,000 citations up to the present.

In addition to the field of statistics, David worked on a broad range of applications. In 2010, he received the Royal Society’s highest award, the Copley Medal, as a recognition of his contributions to science. He held the view that even for a theoretical statistician, it would be extremely fruitful and essential to have serious contact with applications. This guiding principle has played a significant role in shaping my research. Since my PhD, I have been working on some fundamental problems in reinforcement learning and complex data analysis, focusing on developing statistical learning methodologies and establishing their theoretical properties. All these problems are well-motivated from real-world applications, including precision medicine, mobile health, ridesharing, and neuroimaging. Moreover, in the past few years, I have been working closely with applied biostatisticians to help solve their problems.

In 2021, I was very honored to receive the RSS Research Prize, which was endowed by David and later renamed as the David Cox Research Prize. I am deeply grateful for his contributions to our field.

Disclosure Statement

Chengchun Shi has no financial or non-financial disclosures to share for this article.


Cox, D. R. (1975). Partial likelihood. Biometrika, 62(2), 269–227.

Cox, D. R. (1972). Regression models and life-tables. Journal of the Royal Statistical Society (Series B), 34(2), 187–202.

Downing, J. (2022, February 3). Sir David Cox: ‘A giant of statistics with a large place in the hearts of many.’ Cambridge Independent.

Royal Statistical Society. (2020, January 22). Sir David Cox, 1924-2022.

Stats & Data Science Views. (2014, January 24). An interview with Sir David Cox. Wiley.

©2023 Chengchun Shi. This article is licensed under a Creative Commons Attribution (CC BY 4.0) International license, except where otherwise indicated with respect to particular material included in the article.

No comments here
Why not start the discussion?