Skip to main content
Fang Yao
CRM-SSC Prize in Statistics
2014

The CRM-SSC Prize in statistics is awarded annually by the Centre de recherches mathématiques (Montréal) and the Statistical Society of Canada to recognize a statistical scientist's professional accomplishments in research during the first fifteen years after earning a doctorate. This year's winner is Fang Yao of the University of Toronto.

Fang Yao has conducted his most important research since arriving at the University of Toronto in 2006; it is both seminal and beautiful.
 
Fang received his Bachelors degree from the University of Science and Technology in China. He was admitted to the University of California, Davis, for graduate studies, where he completed both his MSc and his PhD in three years. His doctoral dissertation was completed under the joint supervision of Hans-Georg Müller and Jane-Ling Wang. The dissertation was novel for coupling advanced methodological machinery with a data-type critical for establishing causal relationships. Subsequent to completing his degree in 2003, Fang assumed a position in the Department of Statistics at Colorado State University. The Department of Statistical Sciences at the University of Toronto successfully recruited Fang in 2006; he was subsequently promoted to the rank of Associate Professor with tenure in 2008. During his first sabbatical, Fang was invited to the Statistical and Applied Mathematical Sciences Institute in North Carolina as a Research Fellow, where he gave the opening address for a thematic program and subsequently led one of the working groups during the fall term. He then moved on to UBC for the rest of his sabbatical leave, where he created a new advanced graduate course, Topics in Smoothing: Functional Data Analysis.
 
Fang’s expertise is in the area of functional data analysis (FDA), a relatively new field in statistical science that regards data as a set of functions. Fang’s contributions to FDA have been fundamental. His research program, characterized by great ambition and breadth, continues to lay the foundations of FDA by framing it in terms of interpretable models with complex correlation structures that improve the efficiency of inference techniques. Methods he develops are useful for both representation and regression problems, and are accessible through the development of his publicly available software PACE, which has significantly extended the impact of his research in statistical science and other fields. Fang is the consummate statistician, having a deep understanding of rigorous mathematical techniques, a broad statistical knowledge and the ability to apply both in substantive problems.
 
Fang Yao has 30 peer-reviewed publications and is highly cited. His NSERC Discovery grant increased substantially when it was renewed, and was coupled with a Discovery Accelerator Supplement. Fang has made considerable contributions to the profession, particularly in supporting the development of research through his involvement in the organization of workshops, conferences and programs and through his commitment to the review of scholarly work. Fang is an Associate Editor for eight journals, including the Journal of the American Statistical Association, the Annals of Statistics and the Canadian Journal of Statistics.
 
Fang and his wife, Helen, were extremely excited to celebrate the arrival of their first child, Alexander, in the summer of 2013. Fang enjoys outdoor activities, such as skiing, hiking and rock climbing, having been introduced to them in Colorado and California. He also likes playing poker with friends and in local tournaments.
 
Fang Yao will present an overview of his work in a special session at the 42nd Annual Meeting of the Statistical Society of Canada to be held in Toronto, Ontario, May 25 to 28, 2014.

Citation Accompanying the Award / Criteria / Award Delivery

“To Fang Yao, for his foundational, influential and trail-blazing research in the field of functional data analysis; for exploring fruitful connections between longitudinal and functional data, and for demonstrating ways in which tools from the more traditional fields of nonparametric statistics can be successfully leveraged in FDA research.”