Variational Bayesian functional PCA

A Bayesian approach to analyze the modes of variation in a set of curves is suggested. It is based on a generative model thus allowing for noisy and sparse observations of curves. A Demmler-Reinsch(-type) basis is used to enforce smoothness of the latent (`eigen'-)functions. Inference, including estimation, error assessment and model choice, particularly the choice of the number of eigenfunctions and their degree of smoothness, is derived from a variational approximation of the posterior distribution. The proposed analysis is illustrated with simulated and real data. Key words: Variational principal components, functional data analysis, eigenfunctions, rotation, interpolation splines, Demmler-Reinsch basis, Canadian weather data.

• Type: Journal
• Year: 2008
• Where: CSDA
• Authors: Angelika van der Linde
• Keywords: Bayesian Approach, CSDA 2008, Generative Model, Variational Principal Components