Richard D. Gill
|Richard David Gill|
Richard D. Gill
11 September 1951|
University of Cambridge|
Free University of Amsterdam (PhD)
|Doctoral students||Sara van de Geer, Mark van der Laan|
Richard David Gill (born 11 September 1951) is a mathematician born in the United Kingdom who has lived in the Netherlands since 1974. As a probability theorist and statistician, Gill is most well known for his research on counting processes and survival analysis, some of which has appeared in an advanced textbook. He is the chair of mathematical statistics at Leiden University. Gill is also known for his pro bono consulting and advocacy on behalf of victims of incompetent statistical testimony, including a Dutch nurse who was wrongfully convicted and jailed for six years.
He studied mathematics at the University of Cambridge (1970–1973), and subsequently followed the Diploma of Statistics course there (1973–1974).
Marrying a Dutch woman, he moved to the Netherlands where he worked from 1974 to 1988 at the Mathematical Centre (later renamed Centrum Wiskunde & Informatica, or CWI) of Amsterdam. In 1979, Gill obtained his PhD with the thesis Censoring and Stochastic Integrals, which was supervised by Jacobus Oosterhoff of the Vrije Universiteit, which awarded the doctorate. Gill spent Autumn 1980 at the Statistical Research Unit at the University of Copenhagen. Gill continued to collaborate with Danish (and Norwegian) statisticians for ten years, helping to write the book Statistical models based on counting processes, which is often referred to as "ABGK" (for the authors Andersen, Borgan, Gill, and Keiding). In 1983 he became the head of the Department of Mathematical Statistics at CWI.
In 1988 he moved to the Department of Mathematics of Utrecht University. Gill became the chair in mathematical stochastics—this chair represented the three mathematical sciences of mathematical statistics, probability theory, and operations research. His PhD students include Sara van de Geer and Mark van der Laan.
In 2006, he moved to the Department of Mathematics at Leiden University, where he became the chair of mathematical statistics. Since then, he has conducted statistical research in the theory of quantum information and in biostatistics. He has also worked on survival analysis, semiparametric models, causality, missing data, machine learning, and statistics in image analysis. Gill also publishes on the foundations of several mathematical sciences: the foundations of statistics, of probability, of mathematics, and of quantum physics.
Statistical advocacy against wrongful convictions
In recent years he has lobbied for retrials for Lucia de Berk and Kevin Sweeney. The nurse Lucia de Berk was sentenced to life imprisonment, after a legal psychologist gave testimony that there was great likelihood that de Berk committed a string of murders.
"The court was told by Dr Henk Elffers of the Netherlands Institute for the Study of Crime and Law Enforcement that more children had died on her shifts than appeared possible by chance. He put the odds of her presence being a mere coincidence at one in 342 million, a figure that seemed to have blinded the court to any alternative explanation of the deaths."
This statistical testimony was shown to be fallacious by professional statisticians, notably Gill. Continued scrutiny showed that the data had also been collected to support the prosecutor's conviction of Berk, which further invalidated the pseudo-statistical testimony.
"The conduct of the case, in Professor Gill's account, was extraordinary. Convinced she was guilty, the police and the managers of the Juliana Children's Hospital assembled a dossier in which it seemed every death became unnatural when it had occurred during, or after, a shift in which she had worked. For one of the alleged murders, it was established on appeal she had not even been in the hospital for three days around the time it occurred. Using more appropriate statistical methods reduced the odds from one in 342 million to one in 48. A further analysis by Professor Gill further reduces the odds to one in nine."
Professor Gill helped in the campaign to have a new trial. Consequently, a retrial was ordered, and de Berk was found not guilty, and received a public apology from the Dutch government, along with financial compensation (amount unknown) for her six years of incarceration.
Richard Gill is a member of the Royal Netherlands Academy of Arts and Sciences. He is a past president of The Netherlands Society for Statistics and Operations Research, which publishes the journal Statistica Neerlandica. Gill was selected as the 2010–2011 Distinguished Lorentz Fellow by the Netherlands Institute for Advanced Study in Humanities and Social Sciences.
- Richard David Gill at the Mathematics Genealogy Project
- Andersen, Per Kragh; Borgan, Ørnulf; Gill, Richard D.; Keiding, Niels (1993). Statistical models based on counting processes. Springer series in statistics. New York: Springer-Verlag. pp. xii+767. ISBN 0-387-97872-0. MR 1198884.
- Hawkes, Nigel (10 April 2010). "Did statistics damn Lucia de Berk?: Behind the numbers". The Independent (London).
- Mark Buchanan (18 January 2007). "Statistics: conviction by numbers" (PDF). Nature. 445 (7125): 254–255. Bibcode:2007Natur.445..254B. doi:10.1038/445254a. PMID 17230166.
- Persbericht CWI Archived 8 April 2008 at the Wayback Machine. Petitie 2 November 2007
- "Expert on the most important proof in the Lucia de B. case: 'This baby has not been poisoned'". Archived 4 October 2008 at the Wayback Machine. NOVA. 29 September 2007.
- "Nurse Lucia de Berk finally found not guilty of murdering seven patients". 14 April 2010. Archived from the original on 24 July 2011.
- "Apology for nurse jailed for murdering seven patients", AP, The Independent 14 April 2010.
- "Richard Gill" (in Dutch). Royal Netherlands Academy of Arts and Sciences. Retrieved 15 July 2015.
- Board, Netherlands Society for Statistics and Operations Research. Accessed 23 January 2010
- Richard Gill Distinguished Lorentz Fellow 2010–2011, News release, Leiden University. Accessed 23 January 2010.