Semiparametric methods for inference of spatial and spatio-temporal stochastic processes

• Grant number: 19/03517-0
• Support Opportunities: Regular Research Grants
• Start date: May 01, 2019
• End date: April 30, 2020
• Field of knowledge: Physical Sciences and Mathematics - Probability and Statistics - Statistics
• Principal Investigator: Guilherme Vieira Nunes Ludwig
• Grantee: Guilherme Vieira Nunes Ludwig
• Host Institution: Instituto de Matemática, Estatística e Computação Científica (IMECC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil

Abstract

Semiparametric models are frequently employed in spatial statistics, but the high dimensionality of data coming from scientific experiments is causing computational scalability problems to existing semiparametric methods. This project seeks to develop scalability solutions to three semiparametric methods -- namely, data fusion of spatio-temporal processes, esimation of nonstationary covariance functions via spatial deformations, and estimating equation approaches to spatial point processes. The project will also build software that implements the proposed techniques. (AU)