Irregularly Sampled Time Series Models

• Grant number: 25/22112-2
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: November 01, 2025
• End date: October 31, 2026
• Field of knowledge: Physical Sciences and Mathematics - Probability and Statistics - Statistics
• Principal Investigator: Aluísio de Souza Pinheiro
• Grantee: Luiz Augusto Cortez Silva
• 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

Time series analysis on both time domain and frequency domain is based on regular sampling intervals. Notwithstanding this paradigm, several problems are burdened by missing data, such as meteorological problems. Researchers usually replace the missing data points (Afrifa-Yamoah et al., 2020) so that the general time series algorithms can be applied. On the other hand, certain natural and technological phenomena can only be observed in irregular intervals. Two examples are astronomical data (Echeverri, 2019; Elorrieta et al., 2019) and satellite images (Fonseca et al., 2023). Straightforward solutions would be methodologically more appropriate than the usual data augmentation/ regular time series analysis.The irregularly sampled time series has been a historical concern in the scientific literature (Parzen, 1984). Solutions are in general approximate or very specific. New methodologies which allow for the systematic study of irregular time series have recently arisen and are this project's focus. Giraitis and Marotta (2023) and Wifredo Palma and collaborators (Elorireta et al., 2019) present novel models for irregular time series. In this project these two proposals will be studied, extended and applied to real data. (AU)