BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250713T072013EDT-1083uXUuJP@132.216.98.100
DTSTAMP:20250713T112013Z
DESCRIPTION:How Small Data Can Leverage Big Data\n\nBhramar Mukherjee is a 
 John D. Kalbfleisch Collegiate Professor and Associate Chair of the Depart
 ment of Biostatistics\; Professor\, Department of Epidemiology\, Professor
  of Global Public Health\, University of Michigan School of Public Health.
  She is a Research Professor in Michigan Institute of Data Science. She is
  the Associate Director for Cancer Control and Population Sciences at the 
 University of Michigan Comprehensive Cancer Center. Her research interests
  include Statistical methods for studies of gene-environment interaction\,
  case-control studies and outcome dependent sampling\, Bayesian methods\, 
 shrinkage estimation\, optimal designs\, applications in cancer\, cardiova
 scular diseases\, exposure science and environmental epidemiology. She has
  co-authored more than 180 peer-reviewed papers. She is a fellow of the Am
 erican Statistical Association and has received many awards among which th
 e Gertrude Cox Award in 2016 from the Washington Statistical Society\, the
  John D. Kalbfleisch Collegiate Professorship from the University of Michi
 gan in 2015\, the University of Michigan mid-career Faculty Recognition Aw
 ard in 2015 and the Outstanding young researcher award (applications categ
 ory)\, International Indian Statistical Association in 2014.\n\n	We are liv
 ing at a time when the “Big Data” movement is raging across the world\, re
 volutionizing and stretching our computational imagination\, when being a 
 data scientist is perhaps more attractive than being a statistician to the
  new generation of quantitative scientists. This lecture will aim to illus
 trate how classical statistical principles can be used to incorporate exte
 rnal auxiliary information available from large data sources in improving 
 inference based on a current dataset of modest size. We will consider thre
 e examples from biomedical sciences. (1) A new assaying technology is repl
 acing the current practice: we have a large dataset measured in the old pl
 atform and a small sub-sample measured on the new one\; can the old one he
 lp in boosting prediction of patient outcomes? (2) A new biomarker/predict
 or is being proposed to be added to an existing prediction model: while we
  have abundant published data on the established prediction model\, the ne
 w biomarker is available on a smaller sample\; can the existing informatio
 n be used in a principled way to improve prediction under the new model? (
 3) We have a convenience sample of patients in a health system with access
  to their complete electronic medical records and genomewide scans: can we
  use knowledge from large population-based genome-wide association studies
  to learn and discover in this biased sample? Through these three examples
 \, I will try to identify a connecting theme advocating for timeless stati
 stical principles and study designs to be applied to cutting-edge problems
  in biomedical sciences.\n
DTSTART:20171024T193000Z
DTEND:20171024T203000Z
LOCATION:Room 24\, Purvis Hall\, CA\, QC\, Montreal\, H3A 1A2\, 1020 avenue
  des Pins Ouest
SUMMARY:Bhramar Mukherjee\, PhD\, University of Michigan
URL:/mathstat/channels/event/bhramar-mukherjee-phd-uni
 versity-michigan-279848
END:VEVENT
END:VCALENDAR