High-dimensional variable selection

Add to your list(s) Download to your calendar using vCal

• Richard Samworth, Statistical Laboratory, University of Cambridge
• Thursday 20 February 2014, 19:15-21:30
• Department of Plant Sciences, Downing Site, Cambridge .

If you have a question about this talk, please contact Peter Watson.

We live in the era of Big Data, where it is often relatively cheap to collect and store vast quantities of data. While this presents unprecendented opportunities to improve our scientific understanding and quality of life, there are also substantial statistical challenges. One of the most important of these is variable selection, and it is a topic that has received enormous attention among statisticians over the last 15 years or so.

I will describe some methods that have been proposed, and outline some of my own work, in collaboration with Rajen Shah, that aims to improve the performance of any existing variable selection algorithm through Complementary Pairs Stability Selection.

This talk is part of the Cambridge Statistics Discussion Group (CSDG) series.

This talk is included in these lists:

• All CMS events
• All Talks (aka the CURE list)
• BHRU Annual Lecture 2015
• BHRU Annual Lecture 2016
• CMS Events
• Cambridge Statistics Discussion Group (CSDG)
• Cardiovascular Epidemiology Unit Special Seminars
• DPMMS Lists
• DPMMS info aggregator
• DPMMS lists
• Department of Plant Sciences, Downing Site, Cambridge
• Department of Public Health and Primary Care
• Hanchen DaDaDash
• Interested Talks
• PublicHealth@Cambridge
• School of Physical Sciences
• Statistical Laboratory info aggregator
• bld31

Note that ex-directory lists are not shown.