Clay Public Lecture: "Technology-driven statistics" 

 The Clay Mathematics Institute and the Harvard Mathematics Department are sponsoring a lecture by Terry Speed from the Department of Statistics at Berkeley on "Technology-driven statistics," with a focus on the challenges presented to statistical theory and practice presented by the massive amounts of data that are generated by modern scientific instruments (microarrays, mass spectrometers, etc.).  These issues have not yet been as salient in the social sciences, but they are clearly on the horizon.  The talk is at 7PM tonight (Oct. 30) in Science Center B at Harvard.  The abstract for the talk is after the jump: 


 Technology-driven Statistics 

 Terry Speed, UC Berkeley and WEHI in Melbourne, Australia 

 Tuesday, October 30, 2007, at 7:00 PM 

 Harvard University Science Center -- Hall B 

  
Forty years ago, biologists collected data in their notebooks. If they needed help from a statistician in analyzing and interpreting it, they would pass over a piece of paper with numbers on it. The theory on which statistical analyses was built a couple of decades earlier seemed entirely adequate for the task. When computers became widely available, analyses became easier and a little different. with the term "computer intensive" entering the lexicon. Now, in contemporary biology and many other areas, new technologies generate data whose quantity and complexity stretches both our hardware and our theory. Genome sequencing, genechips, mass spectrometers and a host of other technologies are now pushing statistics very hard, especially its theory. Terry Speed will talk about this revolution in data availability, and the revolution we need in the way we theorize about it. 

 Terry Speed splits his time between the Department of Statistics at the University of California, Berkeley and the Walter & Eliza Hall Institute of Medical Research (WEHI) in Melbourne, Australia. Originally trained in mathematics and statistics, he has had a life-long interest in genetics. After teaching mathematics and statistics in universities in Australia and the United Kingdom, and a spell in Australia's Commonwealth Scientific and Industrial Research Organization, he went to Berkeley 20 years ago. Since that time, his research and teaching interests have concerned the application of statistics to genetics and molecular biology. Within that subfield, eventually to be named bioinformatics, his interests are broad, including biomolecular sequence analysis, the mapping of genes in experimental animals and humans, and functional genomics. He has been particularly involved in the low level analysis of microarray data. Ten years ago he took the WEHI job, and now spends half of his time there, half in Berkeley, and the remaining half in the air somewhere in between.