Proposal Description

The increasing complexity of modern data often manifests itself within functional, non-Euclidean, or metric spaces. These complex data structures are prevalent in diverse fields such as medical imaging, computational biology, and computer vision. In response to these challenges, our session is designed to delve into the depths of innovative methodologies and robust frameworks that address the statistical intricacies inherent in both functional and object data analysis domains.

The focal points of our session encompass the perplexing estimation and prediction within functional linear models (FLR) with sparse functional Covariates, unveiling the potential of functional principal component analysis (FPCA) in spatially and temporally indexed point processes. Furthermore, we will investigate statistical models tailored for samples of distribution-valued stochastic processes, and the regression analysis and graphical modeling of point process data.

Our presentation anticipates a wide-reaching audience across diverse fields, particularly from applied disciplines spanning neuroscience, healthcare research, genetics, and machine learning.