Speakers: John Abowd (Cornell) and Ping Li (Cornell and Rutgers)
Title: Boosting Models for Edit, Imputation and Prediction of Multiple Response Outcomes
Abstract: In this paper, we propose a statistical framework that generalizes the classical logit model to predict multiple responses (i.e., multi-label classification). We develop an effective implementation based on boosting and trees. For the NCRN seminar we present an application to editing and imputation in the multiple response race and ethnicity coding on the American Community Survey.
º Duke University: contact Alan Karr (firstname.lastname@example.org)
º Carnegie Mellon: contact William Eddy (email@example.com)
º Cornell University, Ithaca campus: Ives 381
º Census Bureau headquarters: Room T-1, contact Dan Weinberg (firstname.lastname@example.org)
º University of Michigan: Room 368 ISR-Thompson
º University of Missouri: contact Scott Holan (email@example.com)
º University of Nebraska-Lincoln: 301 Canfield Hall: contact: Allan McCutcheon (firstname.lastname@example.org)
º Northwestern University: contact Zach Seeskin (email@example.com)
- Live video conference. Please contact Lars Vilhuber (firstname.lastname@example.org) if you wish to participate by video conference, by Monday, February 3, 2014.