The Kingsman Prize was established in memory of the long-standing scholar of Management Science, Professor Brian Kingsman. The 2021 prize has been awarded to STOR-i PhD graduate Faye Williamson.

Faye’s supervisor Peter Jacko has written the following citation:

“Faye was a STOR-i PhD student and started to work on her PhD under the co-supervision of myself and Prof. Thomas Jaki from the Department of Mathematics and Statistics in 2014. Her first piece of research was submitted in early 2016 to the Young Statistician Showcase Competition of the International Biometric Society. The Competition Committee received almost 50 submissions and chose five, one from each continent, and Faye was awarded as the best from Europe. This award came with a support in the sum of $3,000.00 (USD) to attend the International Biometric Conference (held in Canada in 2016) to present the work.

Faye was also the Student Competition Winner of the PSI (Statisticians in the Pharmaceutical Industry) Conference in 2017. Faye's first journal paper was submitted in January 2016, was accepted in September 2016 in the journal “Computational Statistics and Data Analysis” (an ABS-3 journal), and was eventually published as [1]. The paper has since received a very high number of citations (57 in Google Scholar, 24 in Scopus), which is extremely unusual for a methodological paper, and it was listed among the "Top Cited" papers on the journal webpage (2017-2020).

In October 2017 - April 2018 Faye was awarded a paid 6-month Research Assistant internship at the Biostatistics Unit at University of Cambridge, which resulted in submission of another journal paper in June 2018 and was eventually published as [2] in the journal “Biometrics” (https://onlinelibrary.wiley.com/journal/15410420), which is a highly-regarded journal (Q1) in Statistics & Probability. She continued her research to discover a considerable amount of results, one of which is published in the journal “Computational Statistics and Data Analysis” (an ABS-3 journal) and another one is now in preparation for submission to the “Journal of the Royal Statistical Society – Series B” (an ABS-4 journal).

She submitted her thesis entitled "Bayesian bandit models for the design of clinical trials", which included all the above research in November 2019, passed her viva in February 2020 and was awarded a PhD degree in Statistics and Operational Research in April 2020. In her research, Faye has successfully managed to work at an interdisciplinary intersection between Management Science and Statistics, in particular innovatively leveraging the statistical decision theory and the so-called bandit models in order to bring the theoretical solutions closer to the practice of clinical trials, in which multiple objectives - e.g. ethics and cost - compete. In particular, her thesis helps bridge the gap between theory and practice by addressing key issues that have prevented bandit models from being implemented in practice, especially for clinical trials of rare diseases for which a development of treatments is challenging due to the limited number of patients available.

During her PhD studies, Faye was a proactive and supportive person, volunteering to work as a Graduate Teaching Assistant at Lancaster University, as a support worker to dyslexic or disabled students, and as a student helper at several academic events.

[1] Williamson, S. F., Jacko, P., Villar, S. S., & Jaki, T. (2017). A Bayesian adaptive design for clinical trials in rare diseases. Computational statistics & data analysis, 113, 136-153. https://doi.org/10.1016/j.csda.2016.09.006

[2] Williamson, S. F., & Villar, S. S. (2020). A response‐adaptive randomization procedure for multi‐armed clinical trials with normally distributed outcomes. Biometrics, 76(1), 197-209. https://doi.org/10.1111/biom.13119

[3] Williamson, S. F., Jacko, P., and Jaki, T. (2021). Generalisations of a Bayesian decision-theoretic randomisation procedure and the impact of delayed responses. Computational Statistics and Data Analysis. Available online 7 December 2021. https://doi.org/10.1016/j.csda.2021.107407