UW Biiostatistics & Medical Informatics UW Biostatistics & Medical Informatics UW Madison UW Biostatistics & Medical Informatics Site Map
UW School of Medicine and Public Health UW Madison



Other Seminar Series


General Departmental Seminar Series

Penalized Functional Principal Components Analysis
Using a Kullback-Leibler Criterion

Robert Krafty
University of Pennsylvania
Biostatistics/Statistics Joint Faculty Candidate

Wednesday, February 28, 2007, 12:00-1:00

140 Bardeen



In this talk, I propose a new data driven penalized method for performing functional principal components analysis. The penalty is based on a regularity of the underlying covariance function that is characterized by the balance between the decays of the eigenvalues and smoothness of the eigenfunctions.  I propose to use the Kullback-Leibler distance to directly measure the goodness-of-fit in the space of functional covariances. A leave-one-trajectory-out cross validation procedure is introduced to estimate this Kullback-Leibler distance that allows for the selection of the smoothing parameter and the number of principal components.

Asymptotic consistency rates are computed which show that procedures selecting smoothing parameters based on metrics over the space of subject trajectories behave sub-optimally. Simulation studies are presented to demonstrate the method's empirical properties, while its practical  relevance is illustrated through the analysis of time-course gene  expression of the temporal transcriptional response of human  fibroblast to serum.

Return to seminar list


Internal Use | Site Map | Search |
Overview | People | Training | Research | Seminars | Employment | Links |
Biostatistics Program | Clinical Trials Program | Medical Informatics Program | Biomedical Computing |

Copyright © 2006 The Board of Regents of the
University of Wisconsin System


UW Madison UW School of Medicine and Public Health