Project's homepage

Summary: Estimating and monitoring the incidence rates of infectious diseases are important for the continuous assessment of the health conditions of a population. Such indicators represent essential aspects of the international development agenda related to the United Nations’ Sustainable Development Goals for 2030. However, the underreporting of cases is a barrier to identifying the true magnitude of the disease and prevents reliable decision-making, especially in less developed regions. The temporal analysis of health-related indicators at small geographic levels can collaborate in development of more efficient public policies aimed at eradicating poverty and promoting good health and well-being. In this context, although there is a growing demand for evaluation of official statistics at more disaggregated spatial levels over time, there is a lack of adequate statistical methods for this purpose in scenarios with evident data misreporting. In this project we aim to define novel different classes of models, study their statistical properties and present case studies to illustrate their usefulness in estimating infectious diseases incidence in many underdeveloped countries where data tends to be underreported. Therefore, the project results can play an important role in more reliable monitoring of health aspects of sustainable development, which is a concern on political agendas worldwide.

Team: Guilherme Lopes de Oliveira (coordinator); Rosangela Helena Loschi (colaborator from UFMG, Brazil); Alexandra Schmidt (colaborator from McGill University, Canada); Wagner Barreto de Souza (colaborator from University Dublin, Ireland); Guilherme Augusto Veloso (colaborator from UFF, Brazil); Jussiane Nader Gonçalves (colaborator from UFMG, Brazil); Gabriela Oliveira (colaborator from IFMG, Brazil); Vinícius Lara Fonseca (Master student from UFMG, Brazil); Maria Cecília Lopes (undergraduate student from UFMG, Brazil).

Funding: Instituto Serrapilheira, Brazil (Grant number: Serra – R-2401-47519. Period: 2024-2029); and FAPEMIG (Fundação de Amparo à Pesquisa do Estado de Minas Gerais), Brazil (Grant number: APQ-06488-24. Period: 2025-2030).

Project's homepage

Summary: Underreporting is one of the recurring problems in count data. It occurs when not all data is reported and is very common when analyzing, for example, the occurrence of infectious diseases in underdeveloped regions, crimes and the abundance of animal species in a given environment. Although in recent years there have been proposals for modeling and correcting under-registration, there is a lack of methods that encompass the study of the quality and adequacy of data with a spatial structure and, at the same time, accommodate the joint analysis of different outcomes involved in a similar context, such as the abundance of different species of animals in the same environment or the occurrence of related crimes in the same region. This project intends to develop non-trivial adaptations both in terms of statistical modeling and its computational implementation, aiming to deal with under-registration and expand the applicability of methods in multivariate contexts with the presence of spatial dependence between the observed data. Applications will focus on environmental and social indicators linked to the Sustainable Development Goals (SDGs) of the United Nations 2023 Agenda.

Team: Guilherme Lopes de Oliveira (coordinator); Marcos Oliveira Prates (colaborator from UFMG, Brazil); Rosangela Helena Loschi (colaborator from UFMG, Brazil); Michael Willig (colaborator from University of Connecticut, US); Guilherme Augusto Veloso (colaborator from UFF, Brazil); Samuel (Master student from UFMG, Brazil); Matheus (Master student from UFMG, Brazil).

Funding: FAPEMIG (Fundação de Amparo à Pesquisa do Estado de Minas Gerais), Brazil (Grant number: APQ-01748-24. Period: 2024-2027).