This talk is just a review of the paper "A multivariate functional-data mixture model for spatio-temporal data: inference and cokriging," which is written by Moritz Korte-Stapff, Drew Yarger, Stilian Stoev, and Tailen Hsing. In their paper, they introduce a mixture model that can be used to perform spatio-temporal prediction when both the response and the additional covariates are functional data. The proposed model is applied on Argo oceanographic data in the Southern Ocean to predict oxygen concentration. We hope that this talk can be a good starter to form a research group about spatial-temporal data analysis. Discussion and comments are very welcome.

Please click here for participating the talk online.