TY - JOUR
T1 - Hierarchical adaptive regression kernels for regression with functional predictors
AU - Woodard, Dawn B.
AU - Crainiceanu, Ciprian
AU - Ruppert, David
N1 - Funding Information:
The authors thank the referees and Associate Editor for their thorough reading and excellent recommendations, and Jeff Goldsmith for providing software and assistance in using PFR. Drs. Crainiceanu and Ruppert are supported by the grant R01NS060910 from the National Institute of Neurological Disorders and Stroke, and Dr Woodard is supported by the National Science Foundation grant CMMI-0926814. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institute of Neurological Disorders and Stroke or the National Institutes of Health.
PY - 2013
Y1 - 2013
N2 - We propose a new method for regression using a parsimonious and scientifically interpretable representation of functional predictors. Our approach is designed for data that exhibit features such as spikes, dips, and plateaus whose frequency, location, size, and shape varies stochastically across subjects. We propose Bayesian inference of the joint functional and exposure models, and give a method for efficient computation. We contrast our approach with existing state-of-the-art methods for regression with functional predictors, and show that our method is more effective and efficient for data that include features occurring at varying locations. We apply our methodology to a large and complex dataset from the Sleep Heart Health Study, to quantify the association between sleep characteristics and health outcomes. Software and technical appendices are provided in the online supplementary materials.
AB - We propose a new method for regression using a parsimonious and scientifically interpretable representation of functional predictors. Our approach is designed for data that exhibit features such as spikes, dips, and plateaus whose frequency, location, size, and shape varies stochastically across subjects. We propose Bayesian inference of the joint functional and exposure models, and give a method for efficient computation. We contrast our approach with existing state-of-the-art methods for regression with functional predictors, and show that our method is more effective and efficient for data that include features occurring at varying locations. We apply our methodology to a large and complex dataset from the Sleep Heart Health Study, to quantify the association between sleep characteristics and health outcomes. Software and technical appendices are provided in the online supplementary materials.
KW - Electroencephalogram
KW - Functional data analysis
KW - Functional linear model
KW - Kernel mixture
KW - Lévy adaptive regression kernels
KW - Nonparametric Bayes
UR - http://www.scopus.com/inward/record.url?scp=84880971274&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84880971274&partnerID=8YFLogxK
U2 - 10.1080/10618600.2012.694765
DO - 10.1080/10618600.2012.694765
M3 - Article
AN - SCOPUS:84880971274
SN - 1061-8600
VL - 22
SP - 777
EP - 800
JO - Journal of Computational and Graphical Statistics
JF - Journal of Computational and Graphical Statistics
IS - 4
ER -