A special feature of Probability and Statistics Day at UMBC 2013 is that the conference, including the workshop, is open to all statistics graduate students
from UMBC and local universites free of charge; however, REGISTRATION IS REQUIRED! The deadline to register is Friday,
April 12, 2013. // REGISTER NOW
For more information, contact any member of the organizing committee:
Bimal Sinha
Conference Chair
443.538.3012
Kofi Adragni
410.455.2406
Yvonne Huang
410.455.2422
Yaakov Malinovsky
410.455.2968
Thomas Mathew
410.455.2418
Nagaraj Neerchal
410.455.2437
DoHwan Park
410.455.2408
Junyong Park
410.455.2407
Anindya Roy
410.455.2435
Elizabeth Stanwyck
410.455.5731
Participant Information
Moumita Karmakar
Paper: Variable selection in complex high dimensional data based on principal fitted components
We develop a variable selection method based on the concept of principal fitted components on high dimensional complex regression data. Principal fitted components are a class of likelihood-based inverse regression methods for a sufficient reduction of the dimensionality of the data. The variable selection procedure is based on a sequential likelihood ratio test and applies in presence of massive number of predictors. Complex regression data implies that the dependency between the predictors and the response is not necessarily linear, but involves nonlinear relationships. We compare the methodology to existing state of the art variable selection approaches when linear model assumptions hold, and study its performance through simulations under various regression setups where these linear model assumptions do not hold.
