Nonparametric functional data analysis through Bayesian Density Estimation

Abel Rodriguez, David B. Dunson and Alan E. Gelfand

Duke University and National Institute of Enviromental Health Sciences

March, 2007

In many modern experimental settings, observations are obtained in the form of functions, and interest lays on inferences on a collection such functions.  Some examples are conductivity-temperature-depth (CTD) data in oceanography, dose-response models in epidemiology and time-course microarray experiments in biology an medicine.  In this paper we propose a hierarchical model that allows us to simultaneously estimate multiple curves nonparametrically by using dependent Dirichlet Process mixtures of Gaussians to characterize the joint distribution of predictors and outcomes.  Function estimates are then induced through the conditional distribution of the outcome given the predictors.  The resulting approach allows for flexible estimation and clustering, while borrowing information across curves. We also show that the function estimates we obtain are consistent on the space of integrable functions.  As an illustration, we consider an application to the analysis of CTD data in the north Atlantic.

Keywords: Nonparametric regressions; Consistency; Functional clustering; Dependent Dirichlet process; Nonparametric Bayes; Random probability measure.


The manuscript is available in PDF format.