arXiv subjects

Rosangela Helena Loschi

Publications and source records attributed to Rosangela Helena Loschi.

4 recordsLinked to original sources

arXiv2026

Bayesian repulsive mixture model for multivariate functional data

We introduce a repulsive mixture model to cluster observation units represented by multivariate functional data, based on similarity of curve shapes and individual-specific covariates. We propose a repulsive prior distribution for the component-specific location parameters that depends on a B-spline curve-tailored distance, extending existent repulsive priors to the context of multivariate functional data. The proposed model favors the identification of well-differentiated clusters, avoiding the presence of redundant ones. To sample from the posterior distribution, we propose an MCMC algorithm that includes a novel split-merge step that significantly improves the chain mixing. Different features of the proposed model, including the effects of repulsion and covariates in the clustering, are evaluated through simulation. The proposed model is fitted to analyze Chronic Ankle Instability (CAI) data, focusing on identifing individuals with similar types of physical dysfunctions based on the similarity of movement patterns.

stat.ME↗

arXiv2025

Modeling temporal dependence in a sequence of spatial random partitions driven by spanning tree: an application to mosquito-borne diseases

Spatially constrained clustering is an important field of research, particularly when it involves changes over time. Partitioning a map is not simple since there is a vast number of possible partitions within the search space. In spatio-temporal clustering, this task becomes even more difficult, as we must consider sequences of partitions. Motivated by these challenges, we introduce a Bayesian model for time-dependent sequences of spatial random partitions by proposing a prior distribution based on product partition models that correlates partitions. Additionally, we employ random spanning trees to facilitate the exploration of the partition search space and to guarantee spatially constrained clustering. This work is motivated by a relevant applied problem: identifying spatial and temporal patterns of mosquito-borne diseases. Given the overdispersion present in this type of data, we introduce a spatio-temporal Poisson mixture model in which mean and dispersion parameters vary according to spatio-temporal covariates. The proposed model is applied to analyze the number of dengue cases reported weekly from 2018 to 2023 in the Southeast region of Brazil. We also evaluate model performance using simulated data. Overall, the proposed model has proven to be a competitive approach for analyzing the temporal evolution of spatial clustering.

stat.ME↗

arXiv2021

Bayesian Dynamic Estimation of Mortality Schedules in Small Areas

The determination of the shapes of mortality curves, the estimation and projection of mortality patterns over time, and the investigation of differences in mortality patterns across different small underdeveloped populations have received special attention in recent years. The challenges involved in this type of problems are the common sparsity and the unstable behavior of observed death counts in small areas (populations). These features impose many dificulties in the estimation of reasonable mortality schedules. In this chapter, we present a discussion about this problem and we introduce the use of relational Bayesian dynamic models for estimating and smoothing mortality schedules by age and sex. Preliminary results are presented, including a comparison with a methodology recently proposed in the literature. The analyzes are based on simulated data as well as mortality data observed in some Brazilian municipalities.

stat.ME↗

arXiv2021

Estimation of underreporting in Brazilian tuberculosis data, 2012-2014

Analysis of burden of underregistration in tuberculosis data in Brazil, from 2012 to 2014. Approches of Oliveira et al. (2020) and Stoner et al. (2019) are applied. The main focus is to illustrated how the approach of Oliveira et al. (2020) can be applied when the clustering structure is not previously available.

stat.AP↗