Hierarchical Bayesian model for predicting spatially correlated curves and with non-equidistant spacing

• Grant number: 23/18036-3
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: August 01, 2024
• End date: July 31, 2026
• Field of knowledge: Physical Sciences and Mathematics - Probability and Statistics - Statistics
• Principal Investigator: Luiz Koodi Hotta
• Grantee: Alvaro Alexander Burbano Moreno
• Host Institution: Instituto de Matemática, Estatística e Computação Científica (IMECC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated research grant: 23/02538-0 - Time series, wavelets, high dimensional data and applications, AP.TEM

Abstract

The primary objective of this research project is to build upon and enhance the findings of Burbano (2023), who introduced a Gaussian functional Bayesian model incorporating B-spline smoothing techniques, Bernstein polynomials, and an autoregressive random effect component. Burbano's model is particularly adept at addressing irregular spacing between data points in each series. In this study, we aim to extend and refine the existing model, detailing these extensions comprehensively within the research project. Subsequently, we intend to apply these enhanced models to a set of real-world data, leveraging them to make predictions in unobserved locations. (AU)