Ciclo de Palestras do PPGE. 

A nossa próxima palestra ocorrerá na quarta-feira, 29 de OUTUBRO. 

Local: Laboratório de Sistemas Estocásticos (LSE), Sala I-044-B, Centro de Tecnologia - UFRJ.

Especialmente nesta data, teremos um seminário duplo, com a seguinte agenda:

- 14h00 às 15h15 

Palestrante: Sugnet Lubbe (Stellenbosch University) 

Título: Multi-dimensional visualisations with biplotEZ

Resumo: Biplots can be viewed as multi-dimensional scatterplots. The rows of a data matrix are represented as sample points while the columns are represented as variable axes. Although the interpretation in terms of samples and variable axes dates from the work of Gower in the 1990’s, the application has be limited by the availability of EZ-to-use software. In this presentation we will look at the basic linear algebra behind two of the most popular forms of biplots: Principal Component Analysis (PCA) biplots and Canonical Variate Analysis (CVA) biplots. Some interesting applications will be used to illustrate the construction of biplots with the biplotEZ R package. Challenges that result from the visualisation of big data will also be discussed as well as some possible solutions.

- 15h15 às 15h30 Coffee break 

- 15h30 às 16h45  

Palestrante: Marcus Nascimento (EMap/FGV)

Título: An Expectation-Maximization algorithm for noncrossing Bayesian quantile regression analysis under informative sampling

Resumo: When quantiles are fitted separately, the resultant regression lines may cross, violating the basic probabilistic rule that quantiles are monotonic functions and possibly causing problems for inference and interpretation in practice. This article introduces a method for handling crossing issues regarding the analysis of complex survey data under informative sampling. Using the location-scale mixture representation of the asymmetric Laplace distribution, we write a joint posterior density function for the quantile levels of interest and develop a constrained Expectation-Maximization algorithm. A model-based simulation study is proposed, and data from the Brazilian National Demographic Health Survey of Women and Children is analyzed to verify and illustrate the algorithm’s effectiveness.

Mais informações: https://ppge.im.ufrj.br/ciclo-de-palestras-segundo-semestre-de-2025/

Organizadores: Maria Eulalia Vares e Widemberg S Nobre