A1015
Title: Robust depth-based registration for multivariate functional data
Authors: Ana Arribas-Gil - Universidad Carlos III de Madrid (Spain) [presenting]
Sara Lopez Pintado - Northeastern University (United States)
Abstract: In the context of multivariate functional data with individual phase variation, a robust depth-based approach is presented to estimate the main pattern function in specific time-warping models. In particular, the latent-deformation model is considered, in which the different components of a multivariate functional variable are also time-distorted versions of a common template function. Rather than focusing on a particular functional depth measure, the necessary conditions of a depth function are discussed to provide a consistent estimation of the central pattern, considering different model assumptions. The method's performance and robustness are evaluated against atypical observations and violations of the model assumptions through simulation and illustrate its use on two real data sets.
